@ARTICLE{DELGRATTA_2021_ARTICLE_DGPC_451726, AUTHOR = {Del Gratta, R. and Goggi, S. and Pardelli, G. and Calzolari, N.}, TITLE = {The LRE Map: what does it tell us about the last decade of our field?}, YEAR = {2021}, ABSTRACT = {The LRE Map of Language Resources was introduced at LREC 2010. Its intended purpose was: "to shed light on the vast amount of resources that represent the background of the research presented at LREC" (Calzolari et al. in: Calzolari et al. (eds) Proceedings of the seventh international conference on language resources and evaluation (LREC'10). European Language Resources Association (ELRA), Valletta, 2010). It also aimed at a change of culture in the field, actively engaging each researcher both in the documentation task about resources and in sharing resources. When we started to use it regularly also in other conferences, it became clear that it was an innovative instrument able to provide a picture of the field and its evolution as reflected by the creation and use of Language Resources. After 9 years we revisit the Map, considerably extending the data analysed in an LREC 2018 paper. The LRE Map data analysed here have been provided by the authors of 21 conferences during the phase of submission of papers, and contain information about 9405 resources. We analyse the LRE Map data from many different viewpoints and the paper reports on the global picture, along the many Map dimensions, on different trends emerging from a diachronic perspective and finally on some comparisons between five editions of the two major conferences present in the Map: LREC and COLING.}, KEYWORDS = {LR infrastucture, metadata, LR documentation}, PAGES = {259-283}, URL = {https://link.springer.com/article/10.1007/s10579-020-09520-6}, VOLUME = {Volume 55}, DOI = {10.1007/s10579-020-09520-6}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @EDITORIAL{BRANCO_2018_EDITORIAL_BCC_401835, AUTHOR = {Branco, A. and Calzolari, N. and Choukri, K.}, TITLE = {4REAL 2018 Workshop on Replicability and Reproducibility of Research Results in Science and Technology of Language Proceedings}, YEAR = {2018}, ABSTRACT = {This workshop sought to contribute to the discussion and the advancement on a topic that has been given insufficient attention in the research area of language processing tools and resources and that has been an important topic emerging in other scientific areas, continuing the objectives of the first edition of the 4REAL workshop, at LREC 2016. We invited the submission of articles that present cases, either with positive or negative results, of actual replication or reproduction exercises of previous published results in our area.}, KEYWORDS = {Reproduction, Replication, Validation}, PAGES = {1-36}, URL = {http://4real2018.di.fc.ul.pt/wp-content/uploads/2018/05/lrec2018_workshop_proceedings_4REAL.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {979-10-95546-21-4}, } @EDITORIAL{CALZOLARI_2018_EDITORIAL_CCCDGHIMMMMOPT_401744, AUTHOR = {Calzolari, N. and Choukri, K. and Cieri, C. and Declerck, T. and Goggi, S. and Hasida, K. and Isahara, H. and Maegaard, B. and Mariani, J. and Mazo, H. and Moreno, A. and Odijk, J. and Piperidis, S. and Tokunaga, T.}, TITLE = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)}, YEAR = {2018}, ABSTRACT = {It is the LREC 20th Anniversary and LREC has become one of the most successful conferences of the field. Data are pervasive in Natural Language Processing and Language Technology: we call our data Language Resources (LR). But when LREC was started by ELRA, in 1998 in Granada, from an idea of Antonio Zampolli and Joseph Mariani, it was really a new adventure and a challenge. There were well established big conferences but he thought that the new emerging field of Language Resources deserved its own dedicated forum. In the keynote talk I gave at LREC1998 I could say: "the infrastructural role of Language Resources as the necessary common platform on which new technologies and applications can be based is nowadays widely recognised." This could not have been said only few years before. I had the pleasure and the honour of being involved in LREC from the beginning, first as member of the Program Committee and since 2004 as Conference Chair.}, KEYWORDS = {Language Resources, Language Technology}, PAGES = {1-4628}, URL = {https://www.aclweb.org/anthology/L18-1}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {979-10-95546-00-9}, } @INPROCEEDINGS{CALZOLARI_2018_INPROCEEDINGS_C_401831, AUTHOR = {Calzolari, N.}, TITLE = {Introduction to LREC 2018 by Nicoletta Calzolari Chair of the 11th edition of LREC ELRA Honorary President}, YEAR = {2018}, ABSTRACT = {It is the LREC 20th Anniversary and LREC has become one of the most successful conferences of the field. Data are pervasive in Natural Language Processing and Language Technology: we call our data Language Resources (LR).}, KEYWORDS = {Language Resources, Language Technology}, PAGES = {1-6}, URL = {https://www.aclweb.org/anthology/L18-1}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {979-10-95546-00-9}, CONFERENCE_NAME = {Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, CONFERENCE_PLACE = {Miyazaki, JAPAN}, CONFERENCE_DATE = {MAY 7-12, 2018}, BOOKTITLE = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, EDITOR = {Calzolari, N. and Choukri, K. and Cieri, C. and Declerck, T. and Hasida, K. and Isahara, H. and Maegaard, B. and Mariani, J. and Moreno, A. and Odijk, J. and Piperidis, S. and Tokunaga, T.}, } @INPROCEEDINGS{DELGRATTA_2018_INPROCEEDINGS_DGPC_387155, AUTHOR = {Del Gratta, R. and Goggi, S. and Pardelli, G. and Calzolari, N.}, TITLE = {LREMap, a Song of Resources and Evaluation}, YEAR = {2018}, ABSTRACT = {After 8 years we revisit the LRE Map of Language Resources, introduced at LREC 2010, to try to get a picture of the field and its evolution as reflected by the creation and use of Language Resources. The purpose of the Map was in fact "to shed light on the vast amount of resources that represent the background of the research presented at LREC". It also aimed at a "change of culture in the field, actively engaging each researcher in the documentation task about resources". The data analysed here have been provided by the authors of several conferences during the phase of submission of papers, and contain information about ca. 7500 resources. We analysed the LRE Map data from many different viewpoints and the paper reports on the global picture, on different trends emerging from the diachronic perspective and finally on some comparisons between the 2 major conferences present in the Map: LREC and COLING.}, KEYWORDS = {LR Infratructure, Metadata, LR Documentation}, PAGES = {1275-1281}, URL = {http://www.lrec-conf.org/proceedings/lrec2018/summaries/300.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {979-10-95546-00-9}, CONFERENCE_NAME = {Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, CONFERENCE_PLACE = {Miyazaki, Japan}, CONFERENCE_DATE = {7-12/05/2018}, BOOKTITLE = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, EDITOR = {Calzolari, N. and Choukri, K. and Cieri, C. and Declerck, T. and Goggi, S. and Hasida, K. and Isahara, H. and Maegaard, B. and Mariani, J. and Mazo, H. and Moreno, A. and Odijk, J. and Piperidis, S. and Tokunaga, T.}, } @EDITORIAL{BRANCO_2017_EDITORIAL_BCVIC_383337, AUTHOR = {Branco, A. and Cohen, K. B. and Vossen, P. and Ide, N. and Calzolari, N.}, TITLE = {Replicability and reproducibility of research results for human language technology: introducing an LRE special section}, YEAR = {2017}, KEYWORDS = {Human Language Technology (HLT), Language Resources (LR)}, PAGES = {1-5}, URL = {https://link.springer.com/article/10.1007/s10579-017-9380-0}, VOLUME = {51}, DOI = {10.1007/s10579-017-9380-0}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, BOOKTITLE = {Language resources and evaluation (Print)}, } @ARTICLE{REHM_2016_ARTICLE_RUABBBBBCDGGGVHHJKKKLMMMMMMOOPPPRRPSDTTTVVVZ_355592, AUTHOR = {Rehm, G. and Uszkoreit, H. and Ananiadou, S. and Bel, N. and Bieleviciene, A. and Borin, L. and Branco, A. and Budin, G. and Calzolari, N. and Daelemans, W. and Garabik, R. and Grobelnik, M. and Garcia Mateo, C. and Van Genabith, J. and Hajic, J. and Hernaez, I. and Judge, J. and Koeva, S. and Krek, S. and Krstev, C. and Linden, K. and Magnini, B. and Mariani, J. and McNaught, J. and Melero, M. and Monachini, M. and Moreno, A. and Odijk, J. and Ogrodniczuk, M. and Pezik, P. and Piperidis, S. and Przepiorkowski, A. and Rognvaldsson, E. and Rosner, M. and Pedersen, B. S. and Skadina, I. and De Smedt, K. and Tadic, M. and Thompson, P. and Tufis, D. and Varadi, T. and Vasiljevs, A. and Vider, K. and Zabarskaite, J.}, TITLE = {The strategic impact of META-NET on the regional, national and international level}, YEAR = {2016}, ABSTRACT = {This article provides an overview of the dissemination work carried out in META-NET from 2010 until 2015; we describe its impact on the regional, national and international level, mainly with regard to politics and the funding situation for LT topics. The article documents the initiative's work throughout Europe in order to boost progress and innovation in our field.}, KEYWORDS = {Language technology, Multilingual technologies, Machine translation, Language resources, META-NET, META-SHARE}, PAGES = {351-374}, URL = {http://link.springer.com/article/10.1007/s10579-015-9333-4}, VOLUME = {50}, DOI = {10.1007/s10579-015-9333-4}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @ARTICLE{RHEM_2016_ARTICLE_RUCM_344298, AUTHOR = {Rhem, G. and Uzkoreit, H. and Calzolari, N. and Monachini, M.}, TITLE = {The strategic impact of META-NET on the regional, national and international level}, YEAR = {2016}, ABSTRACT = {This article provides an overview of the dissemination work carried out in META-NET from 2010 until 2015; we describe its impact on the regional, national and international level, mainly with regard to politics and the funding situation for LT topics. The article documents the initiative's work throughout Europe in order to boost progress and innovation in our field.}, KEYWORDS = {Language technology, Multilingual technologies, Machine translation, Language resources, META-NET, META-SHARE}, PAGES = {26}, URL = {http://www.springer.com/home?SGWID=0-0-1003-0-0\&aqId=2981193\&download=1\&checkval=6c0c2a6da36ef097f2a5e48a49f794e4}, DOI = {10.1007/s10579-015-9333-4}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @EDITORIAL{BRANCO_2016_EDITORIAL_BCC_367184, AUTHOR = {Branco, A. and Calzolari, N. and Choukri, K.}, TITLE = {4REAL Workshop: Workshop on Research Results Reproducibility and Resources Citation in Science and Technology of Language}, YEAR = {2016}, ABSTRACT = {This workshop seeks to foster the discussion and the advancement on a topic that has been so far given insufficient attention in the research area of language processing tools and resources (Branco, 2013, Fokkens et al., 2013) and that has been an important topic emerging in other scientific areas. That is the topic of the reproducibility of research results and the citation of resources, and its impact on research integrity.}, KEYWORDS = {Research Results Reproducibility, Resources Citation}, PAGES = {1-38}, URL = {http://www.lrec-conf.org/proceedings/lrec2016/index.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-9-1}, } @EDITORIAL{CALZOLARI_2016_EDITORIAL_CCDGGMMMMOP_355640, AUTHOR = {Calzolari, N. and Choukri, K. and Declerck, T. and Goggi, S. and Grobelnik, M. and Maegaard, B. and Mariani, J. and Mazo, H. and Moreno, A. and Odijk, J. and Piperidis, S.}, TITLE = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, YEAR = {2016}, ABSTRACT = {Curatela dei 744 articoli presentati alla conferenza LREC2016.}, KEYWORDS = {Language Resources Evaluation}, PAGES = {1-4693}, URL = {http://www.lrec-conf.org/proceedings/lrec2016/index.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-9-1}, } @EDITORIAL{IDE_2016_EDITORIAL_IC_367165, AUTHOR = {Ide, N. and Calzolari, N.}, TITLE = {Editors' introduction to the special issue: papers from LREC 2014}, YEAR = {2016}, KEYWORDS = {Language Resources}, PAGES = {163-164}, URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-84975686215\&origin=inward}, VOLUME = {50}, DOI = {10.1007/s10579-016-9358-3}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, BOOKTITLE = {Language resources and evaluation (Print)}, } @INPROCEEDINGS{CALZOLARI_2016_INPROCEEDINGS_C_367150, AUTHOR = {Calzolari, N.}, TITLE = {Preface: General Chair}, YEAR = {2016}, ABSTRACT = {COLING is organised under the auspices of the International Committee on Computational Linguistics (ICCL, http://nlp.shef.ac.uk/iccl/index.html). ICCL is a very special committee, with no fixed rules and no funding, whose only function is to make sure that aCOLING appears every two years and that it is a good and friendly conference.}, KEYWORDS = {Computational Linguistics}, URL = {http://aclweb.org/anthology/C/C16/C16-1000.pdf}, ISBN = {978-4-87974-702-0}, CONFERENCE_NAME = {The 26th International Conference on Computational Linguistics, COLING 2016}, CONFERENCE_PLACE = {Osaka, Japan}, CONFERENCE_DATE = {December 11-16, 2016}, } @INPROCEEDINGS{CALZOLARI_2016_INPROCEEDINGS_C_367173, AUTHOR = {Calzolari, N.}, TITLE = {Introduction of the Conference Chair and ELRA President Nicoletta Calzolari}, YEAR = {2016}, ABSTRACT = {Chair of the 10th International Conference on Language Resources and Evaluation and ELRA President}, KEYWORDS = {Language Resources}, PAGES = {1-6}, URL = {http://www.lrec-conf.org/proceedings/lrec2016/index.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-9-1}, CONFERENCE_NAME = {LREC 2016, Tenth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Portorose, Slovenia}, CONFERENCE_DATE = {May 23-28, 2016}, BOOKTITLE = {The LREC 2016 Proceedings}, EDITOR = {Calzolari, N. and Choukri, K. and Declerck, T. and Goggi, S. and Grobelnik, M. and Maegaard, B. and Mariani, J. and Mazo, H. and Moreno, A. and Odijk, J. and Piperidis, S.}, } @INPROCEEDINGS{DELGRATTA_2016_INPROCEEDINGS_DFMPRBKSC_355425, AUTHOR = {Del Gratta, R. and Frontini, F. and Monachini, M. and Pardelli, G. and Russo, I. and Bartolini, R. and Khan, F. and Soria, C. and Calzolari, N.}, TITLE = {LREC as a Graph: People and Resources in a Network}, YEAR = {2016}, ABSTRACT = {This proposal describes a new way to visualise resources in the LREMap, a community-built repository of language resource descriptions and uses. The LREMap is represented as a force-directed graph, where resources, papers and authors are nodes. The analysis of the visual representation of the underlying graph is used to study how the community gathers around LRs and how LRs are used in research.}, KEYWORDS = {Language Resources, Resources Documentation, Data Visualisation}, PAGES = {2529-2532}, URL = {http://www.lrec-conf.org/proceedings/lrec2016/index.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-9-1}, CONFERENCE_NAME = {Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, CONFERENCE_PLACE = {Portoroz, Slovenia}, CONFERENCE_DATE = {23-28 may}, EDITOR = {Calzolari, N. and Choukri, K. and Declerck, T. and Goggi, S. and Grobelnik, M. and Maegaard, B. and Mariani, J. and Mazo, H. and Moreno, A. and Odijk, J. and Piperidis, S.}, } @INPROCEEDINGS{POPESCU_2016_INPROCEEDINGS_PLDCC_363731, AUTHOR = {Popescu, V. and Liu, L. and Del Gratta, R. and Choukri, K. and Calzolari, N.}, TITLE = {New Developments in the LRE Map}, YEAR = {2016}, ABSTRACT = {In this paper we describe the new developments brought to LRE Map, especially in terms of the user interface of the Web application, of the searching of the information therein, and of the data model updates. Thus, users now have several new search facilities, such as faceted search and fuzzy textual search, they can now register, log in and store search bookmarks for further perusal. Moreover, the data model now includes the notion of paper and author, which allows for linking the resources to the scientific works. Also, users can now visualise author-provided field values and normalised values. The normalisation has been manual and enables a better grouping of the entries. Last but not least, provisions have been made towards linked open data (LOD) aspects, by exposing an RDF access point allowing to query on the authors, papers and resources. Finally, a complete technological overhaul of the whole application has been undertaken, especially in terms of the Web infrastructure and of the text search backend.}, KEYWORDS = {Language resource, LRE Map, Information search and retrieval, Data modelling}, PAGES = {4526-4530}, URL = {http://www.lrec-conf.org/proceedings/lrec2016/pdf/1256_Paper.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-9-1}, CONFERENCE_NAME = {Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, CONFERENCE_PLACE = {Portoroz, Slovenia}, CONFERENCE_DATE = {23-28/05/2016}, } @INPROCEEDINGS{DELGRATTA_2015_INPROCEEDINGS_DFMPRBGKQSC_342213, AUTHOR = {Del Gratta, R. and Frontini, F. and Monachini, M. and Pardelli, G. and Russo, I. and Bartolini, R. and Goggi, S. and Khan, F. and Quochi, V. and Soria, C. and Calzolari, N.}, TITLE = {Visualising Italian Language Resources: a Snapshot}, YEAR = {2015}, ABSTRACT = {This paper aims to provide a first snapshot of Italian Language Resources (LRs) and their uses by the community, as documented by the papers presented at two different conferences, LREC2014 and CLiC-it 2014. The data of the former were drawn from the LOD version of the LRE Map, while those of the latter come from manually analyzing the proceedings. The results are presented in the form of visual graphs and confirm the initial hypothesis that Italian LRs require concrete actions to enhance their visibility.}, KEYWORDS = {Italian Language Resources}, PAGES = {100-104}, URL = {https://books.openedition.org/aaccademia/1277?lang=it}, ISBN = {978-88-99200-62-6}, CONFERENCE_NAME = {Second Italian Conference on Computational Linguistics CLiC-it 2015}, CONFERENCE_PLACE = {Trento}, CONFERENCE_DATE = {3-4 December 2015}, BOOKTITLE = {Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015}, EDITOR = {Bosco, C. and Tonelli, S. and Zanzotto, F. M.}, } @ARTICLE{SORIA_2014_ARTICLE_SCMQBCMOP_285553, AUTHOR = {Soria, C. and Calzolari, N. and Monachini, M. and Quochi, V. and Bel, N. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S.}, TITLE = {The language resource Strategic Agenda: the FLaReNet synthesis of community recommendations}, YEAR = {2014}, ABSTRACT = {The main purpose of this paper is to serve as a landmark for future research and in particular for future strategic, infrastructural and coordination initiatives. It presents a preliminary plan for actions and infrastructures that could become the basis for future initiatives in the sector of Language Resources and Technologies (LRTs). The FLaReNet Language Resource Strategic Agenda presents a set of recommen- dations for the development and progress of LRT in Europe, as issued from a three- year consultation of the FLaReNet European project. Recommendations cover a broad range of topics and activities, spanning over production and use of language resources, licensing, maintenance and preservation issues, infrastructures for language resour- ces, resource identification and sharing, evaluation and validation, interoperability and policy issues. The intended recipients belong to a large set of players and stakeholders in LRT, ranging from individuals to research and education institutions, to policy- makers, funding agencies, SMEs and large companies, service and media providers}, KEYWORDS = {Strategic agenda, Language resources planning, Recommended priority actions}, PAGES = {753-775}, URL = {https://publications.cnr.it/doc/285553}, VOLUME = {48}, DOI = {10.1007/s10579-014-9279-y}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @INPROCEEDINGS{PIPERIDIS_2014_INPROCEEDINGS_PPSRCHCDMG_288462, AUTHOR = {Piperidis, S. and Papageorgiou, H. and Spurk, C. and Rehm, G. and Choukri, K. and Hamon, O. and Calzolari, N. and Del Gratta, R. and Magnini, B. and Girardi, C.}, TITLE = {META-SHARE: One year after}, YEAR = {2014}, ABSTRACT = {This paper presents META-SHARE (www.meta-share.eu), an open language resource infrastructure, and its usage since its Europe-wide deployment in early 2013. META-SHARE is a network of repositories that store language resources (data, tools and processing services) documented with high-quality metadata, aggregated in central inventories allowing for uniform search and access. META-SHARE was developed by META-NET (www.meta-net.eu) and aims to serve as an important component of a language technology marketplace for researchers, developers, professionals and industrial players, catering for the full development cycle of language technology, from research through to innovative products and services. The observed usage in its initial steps, the steadily increasing number of network nodes, resources, users, queries, views and downloads are all encouraging and considered as supportive of the choices made so far. In tandem, take-up activities like direct linking and processing of datasets by language processing services as well as metadata transformation to RDF are expected to open new avenues for data and resources linking and boost the organic growth of the infrastructure while facilitating language technology deployment by much wider research communities and industrial sectors.}, KEYWORDS = {Infrastructures, language resources identification, language resources documentation, metadata, language resources sharing, language resources licensing}, PAGES = {1532-1538}, URL = {http://www.lrec-conf.org/proceedings/lrec2014/index.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-8-4}, CONFERENCE_NAME = {LREC'14}, CONFERENCE_PLACE = {Reykjavik, Iceland}, CONFERENCE_DATE = {May, 26-31}, BOOKTITLE = {Proceedings of the Ninth International Conference on Language Resources and Evaluation}, EDITOR = {Calzolari, N. and Choukri, K. and Declerck, T. and Loftsson, H. and Maegaard, B. and Mariani, J. and Moreno, A. and Odijk, J. and Piperidis, S.}, } @INPROCEEDINGS{RHEM_2014_INPROCEEDINGS_RUCM_287035, AUTHOR = {Rhem, G. and Uzkoreit, H. and Calzolari, N. and Monachini, M.}, TITLE = {The Strategic Impact of META-NET on the Regional, National and International Level}, YEAR = {2014}, ABSTRACT = {This article provides an overview of the dissemination work carried out in META-NET from 2010 until early 2014; we describe its impact on the regional, national and international level, mainly with regard to politics and the situation of funding for LT topics. This paper documents the initiative's work throughout Europe in order to boost progress and innovation in our field.}, KEYWORDS = {LR National/International Projects, Infrastructural/Policy Issues, Multilinguality, Machine Translation}, PAGES = {1517-1524}, URL = {http://www.lrec-conf.org/proceedings/lrec2014/index.html}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-8-4}, CONFERENCE_NAME = {9th International Conference on Language Resources and Evaluation, LREC 2014}, CONFERENCE_PLACE = {Reykjavik, Iceland}, CONFERENCE_DATE = {26-31 may}, EDITOR = {Calzolari, N. and Choukri, K. and Declerck, T. and Loftsson, H. and Maegaard, B. and Mariani, J. and Moreno, A. and Odijk, J. and Piperidis, S.}, } @ARTICLE{CALZOLARI_2013_ARTICLE_C_288640, AUTHOR = {Calzolari, N.}, TITLE = {Il Trattamento Automatico della Lingua per la sopravvivenza dell'Italiano nel mondo digitale}, YEAR = {2013}, ABSTRACT = {Il TAL nelle sue dimensioni rilevanti}, KEYWORDS = {Trattamento Automatico della Lingua (TAL)}, PAGES = {1-9}, URL = {http://www.camera.it/application/xmanager/projects/leg17/attachments/periodici/pdfs/000/000/007/ritagli_2013_03.pdf}, VOLUME = {2013}, PUBLISHER = {Camera dei Deputati (Roma)}, JOURNAL = {Ritagli}, } @INCOLLECTION{CALZOLARI_2013_INCOLLECTION_C_288554, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources: From Infancy to Maturity. Lessons and Next Steps for the UNL Community}, YEAR = {2013}, ABSTRACT = {In the second chapter, Professor Nicoletta Calzolari Zamorani, Research Associate and former Director of CNR-ILC, Pisa, Italy, approaches the questions by giving insight on the general framework surrounding Language Resources (LRs) today. Rather than answering the specific UNL questions directly, she emphasizes the fact that in order to define a language structure such as UNL it is pree-eminent to gather results of analyses from different communities and to define a coherent strategy.}, KEYWORDS = {Language Resources (LRs)}, PAGES = {19-35}, URL = {https://publications.cnr.it/doc/288554}, PUBLISHER = {Cambridge scholars publishing (Newcastle upon Tyne, GBR)}, ISBN = {978-1-4438-5144-2}, BOOKTITLE = {Lexical Issues of UNL}, EDITOR = {Martins, R.}, } @INCOLLECTION{CALZOLARI_2013_INCOLLECTION_C_288651, AUTHOR = {Calzolari, N.}, TITLE = {The People's web Meets NLP. Collaboratively Constructed Language Resources}, YEAR = {2013}, ABSTRACT = {It's a pleasure to write the Foreword for the book on Collaboratively Constructed Language Resources. I believe that the trend of collaborative construction of Language Resources (LRs) represents both a "natural" evolution of computerised resource building (I'll try to give few historical hints) and a "critical" evolution for the future of the field of language resources}, KEYWORDS = {Language Resources (LRs)}, PAGES = {vii-xiii}, URL = {http://biblioproxy.cnr.it:2107/static/pdf/767/bfm%253A978-3-642-35085-6%252F1.pdf?auth66=1417169875_75f7e71c14e86981c69d52e3379c37e5\&ext=.pdf}, DOI = {10.1007/978-3-642-35085-6}, PUBLISHER = {Springer (Milano-Heidelberg-New York, ITA)}, ISBN = {978-3-642-35085-6}, BOOKTITLE = {The People's Web Meets. NLP Collaboratively Constructed Language Resources}, EDITOR = {Gurevych, I. and Kim, J.}, } @INCOLLECTION{CALZOLARI_2013_INCOLLECTION_CBLM_231482, AUTHOR = {Calzolari, N. and Bertagna, F. and Lenci, A. and Monachini, M.}, TITLE = {Boosting Lexical Resources for the Semantic Web: Generative Lexicon and Lexicon Interoperability}, YEAR = {2013}, ABSTRACT = {To make the vision of a European Information Infrastructure and of the Semantic Web a reality, two key issues are tackled: (i) content, which must be dealt with in a multilingual environment; (ii) standards, which are critical to achieve interoperability and integration. In the Semantic Web scenario, ontologies are the key components to manage knowledge, whereas, in Human Language Technology, semantic description is committed to computational lexicons, which have to squarely address the complexity of natural language. Answers to the above issues are found within two frameworks: first, in the framework of Generative Lexicon (GL) theory and GL-based lexicons that account for the complex, multidimensional and multifaceted nature of meaning in lexicon and ontology design; second, in the context of the ISLE enterprise which, with the MILE, represents an essential interface between advanced research in the field of multilingual lexical semantics and the practical task of developing resources for HLT.}, KEYWORDS = {Generative Lexicon, Computational Lexicons, Standards, Semantic Web, Human Language Technology}, PAGES = {415-431}, URL = {http://download-v2.springer.com/static/pdf/679/chp%253A10.1007%252F978-94-007-5189-7_18.pdf?token2=exp=1430751723~acl=%2Fstatic%2Fpdf%2F679%2Fchp%25253A10.1007%25252F978-94-007-5189-7_18.pdf*~hmac=2ebe0f4a7ba5903ef47dbc16674a886bcbb26b9d6e4e9c9f209e35787522e5f1}, VOLUME = {46}, DOI = {10.1007/978-94-007-5189-7_18}, PUBLISHER = {Springer (Dordrecht, NLD)}, ISBN = {9789400751880}, BOOKTITLE = {Text, Speech and Language Technology}, EDITOR = {Pustejovsky, J. and Bouillon, P. and Isahara, H. and Kanzaki, K. and Lee, C.}, } @INCOLLECTION{CALZOLARI_2013_INCOLLECTION_CMS_280537, AUTHOR = {Calzolari, N. and Monachini, M. and Soria, C.}, TITLE = {LMF-Historical Context and Perspectives}, YEAR = {2013}, ABSTRACT = {The importance of designing standards for language resources (LR) is firmly established, starting with the Expert Advisory Group for Language Engineering (EAGLES) and International Standards for Language Engineering (ISLE) initiatives. Both EAGLES and ISLE stress the importance of reaching a consensus on (linguistic and nonlinguistic) "content", in addition to agreement on formats and encoding issues, and also address the needs of content processing and Semantic Web technologies. The recommendations for standards and best practices issued within the projects became, through the INTERA and mainly the LIRICS project, the International Organization for Standardization (ISO) within the ISO TC37/SC4 committee, where Lexical Markup Framework (LMF) was developed. Standards are fundamental to exchange, preserve, maintain and integrate data and LRs, to achieve interoperability in general, and they are an essential basis of any LR infrastructure.}, KEYWORDS = {EAGLES, international standards for language engineering, interoperability, lexical markup framework (LMF)}, PAGES = {1-18}, URL = {http://dx.doi.org/10.1002/9781118712696.ch1}, DOI = {10.1002/9781118712696.ch1}, PUBLISHER = {John Wiley \& Sons, Inc (Hoboken, USA)}, ISBN = {978-1-118-71259-7}, BOOKTITLE = {LMF Lexical Markup Framework}, EDITOR = {Gil, F. and Patrick, P.}, } @INCOLLECTION{HAYASHI_2013_INCOLLECTION_HMSSC_285427, AUTHOR = {Hayashi, Y. and Monachini, M. and Savas, B. and Soria, C. and Calzolari, N.}, TITLE = {LMF as a Foundation for Servicized Lexical Resources}, YEAR = {2013}, ABSTRACT = {This chapter argues that the lexical markup framework (LMF) can play a significant role in realizing servicized lexical resources on the Web. To accomplish this goal, it begins with a brief introduction of the notion of servicized resources, and then presents a technical architecture of, what is called, LMF-aware lexicon access services. It presents two implementation showcases to demonstrate the applicability of the LMF and to discuss its possible extensions. The first example deals with WordNet-type computational semantic lexicons, while the other takes up a machine-readable bilingual dictionary primarily compiled for human usage. To conclude the chapter, the final sections summarize the results while reviewing related work.}, KEYWORDS = {lexical markup framework (LMF), LMF-aware lexicon access services, servicized lexical resources}, PAGES = {201-213}, URL = {http://onlinelibrary.wiley.com/doi/10.1002/9781118712696.ch14/references}, DOI = {10.1002/9781118712696.ch14}, PUBLISHER = {Wiley-ISTE (Hoboken, USA)}, ISBN = {9781118712696}, BOOKTITLE = {LMF-Lexical Markup Framework}, EDITOR = {Francopoulo, G.}, } @EDITORIAL{SAUR_2013_EDITORIAL_SCHLMP_288143, AUTHOR = {Saurí, R. and Calzolari, N. and Huang, C. R. and Lenci, A. and Monachini, M. and Pustejovsky, J.}, TITLE = {Proceedings of the 6th International Conference on Generative Approaches to the Lexicon Generative Lexicon and Distributional Semantics}, YEAR = {2013}, ABSTRACT = {The papers in this volume represent some of the most recent and exciting work being carried out both within the framework of Generative Lexicon and related approaches to the lexicon and lexical resources. With the recent emphasis in natural language processing on the development of machine learning algorithms, it has become even more important for computational linguists to work on the development of linguistically informed lexical resources, for use in the annotation of corpora and creation of gold standard data for training, as well as the collation of larger theoretical datasets for investigating linguistic phenomena in greater detail and sophistication. These works contribute to this trend as well as to the further development of the mechanisms within GL for describing and explaining semantic and lexical phenomena in language}, KEYWORDS = {Generative Lexicon, Language Resources}, PAGES = {i-126}, URL = {https://aclweb.org/anthology/W/W13/W13-5400.pdf}, PUBLISHER = {Association for Computational Linguistics (Stroudsburg, USA)}, ISBN = {978-1-937284-98-5}, } @ARTICLE{HAYASHI_2012_ARTICLE_HSMSC_218777, AUTHOR = {Hayashi, Y. and Savas, B. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {LMF-aware Web services for accessing semantic lexicons}, YEAR = {2012}, ABSTRACT = {This paper demonstrates that Wordnet-LMF, a version of ISO LMF, allows us to effectively design and implement Web services for accessing WordNettype semantic lexicons that conform to the REST Web service architecture. The implemented prototype service currently provides access to native wordnets as well as to a bilingual concept dictionary. This paper thus describes slight revisions that were made to the Wordnet-LMF specifications to model and accommodate a nonwordnet-native bilingual concept dictionary.}, KEYWORDS = {Lexical markup framework Semantic lexicons Wordnets Language services RESTful Web service design}, PAGES = {253-264}, URL = {http://link.springer.com/content/pdf/10.1007%2Fs10579-012-9181-4.pdf}, VOLUME = {46}, DOI = {10.1007/s10579-012-9181-4}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @ARTICLE{IDE_2012_ARTICLE_IC_288725, AUTHOR = {Ide, N. and Calzolari, N.}, TITLE = {Editors' Note}, YEAR = {2012}, PAGES = {153-154}, URL = {http://biblioproxy.cnr.it:2107/static/pdf/806/art%253A10.1007%252Fs10579-012-9190-3.pdf?auth66=1417189348_cbc23cf949747940b72361b8a4a15351\&ext=.pdf}, VOLUME = {46}, DOI = {10.1007/s10579-012-9190-3}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @BOOK{CALZOLARI_2012_BOOK_CMSS_225736, AUTHOR = {Calzolari, N. and Magnini, B. and Speranza, M. and Soria, C.}, TITLE = {The Italian language in the digital age-La lingua italiana nell'era digitale}, YEAR = {2012}, ABSTRACT = {This white paper is part of a series that promotes knowledge about language technology and its potential. It addresses educators, journalists, politicians, language communities and others. The availability and use of language technology in Europe varies between languages. Consequently, the actions that are required to further support research and development of language technologies also differ for each language. The required actions depend on many factors, such as the complexity of a given language and the size of its community. META-NET, a Network of Excellence funded by the European Commission, has conducted an analysis of current language resources and technologies. This analysis focused on the 23 official European languages as well as other important national and regional languages in Europe. The results of this analysis suggest that there are many significant research gaps for each language. A more detailed expert analysis and assessment of the current situation will help maximise the impact of additional research and minimize any risks. META-NET consists of 54 research centres from 33 countries that are working with stakeholders from commercial businesses, government agencies, industry, research organisations, software companies, technology providers and European universities. Together, they are creating a common technology vision while developing a strategic research agenda that shows how language technology applications can address any research gaps by 2020.}, KEYWORDS = {digital extinction, tecnologie del linguaggio, lingua italiana}, PAGES = {69}, URL = {http://www.springer.com/computer/ai/book/978-3-642-30775-1}, DOI = {10.1007/978-3-642-30776-8}, PUBLISHED = {White Paper Series}, PUBLISHER = {Springer (Berlin, DEU)}, ISBN = {978-3-642-30775-1}, EDITOR = {Rehm, G. and Uszkoreit, H.}, } @INPROCEEDINGS{CALZOLARI_2012_INPROCEEDINGS_CDFMRRS_220194, AUTHOR = {Calzolari, N. and Del Gratta, R. and Francopoulo, G. and Mariani, J. and Rubino, F. and Russo, I. and Soria, C.}, TITLE = {The LRE Map. Harmonising Community Descriptions of Resources}, YEAR = {2012}, ABSTRACT = {Accurate and reliable documentation of Language Resources is an undisputable need: documentation is the gateway to discovery of Language Resources, a necessary step towards promoting the data economy. Language resources that are not documented virtually do not exist: for this reason every initiative able to collect and harmonise metadata about resources represents a valuable opportunity for the NLP community. In this paper we describe the LRE Map, reporting statistics on resources associated with LREC2012 papers and providing comparisons with LREC2010 data. The LRE Map, jointly launched by FLaReNet and ELRA in conjunction with the LREC 2010 conference, is an instrument for enhancing availability of information about resources, either new or already existing ones, reinforcing and facilitating the use of standards in the community. The LRE Map web interface provides the possibility of searching according to a fixed set of metadata and to view the details of extracted resources. The LRE Map is continuing to collect bottom-up input about resources from authors of other conferences through standard submission process. This will help broadening the notion of "language resources" and attract to the field neighboring disciplines that so far have been only marginally involved by the standard notion of language resources.}, KEYWORDS = {Language resources, metadata, documentation}, PAGES = {1084-1089}, URL = {http://www.lrec-conf.org/proceedings/lrec2012/index.html}, ISBN = {978-2-9517408-7-7}, CONFERENCE_NAME = {The Eight International Conference on Language Resources and Evaluation (LREC'12)}, CONFERENCE_PLACE = {Istanbul, Turkey}, CONFERENCE_DATE = {23-25 May 2012}, BOOKTITLE = {Proceedings of LREC'12-The Eight International Conference on Language Resources and Evaluation}, EDITOR = {Calzolari, E. N. and Choukri, K. and Declerck, T. and Doğan, M. U. and Maegaard, B. and Mariani, J. and Idijk, J. and Piperidis, S.}, } @INPROCEEDINGS{DELGRATTA_2012_INPROCEEDINGS_DFRRC_220182, AUTHOR = {Del Gratta, R. and Frontini, F. and Rubino, F. and Russo, I. and Calzolari, N.}, TITLE = {The Language Library: supporting community effort for collective resource production}, YEAR = {2012}, ABSTRACT = {Relations among phenomena at different linguistic levels are at the essence of language properties but today we focus mostly on one specific linguistic layer at a time, without (having the possibility of) paying attention to the relations among the different layers. At the same time our efforts are too much scattered without much possibility of exploiting other people's achievements. To address the complexities hidden in multilayer interrelations even small amounts of processed data can be useful, improving the performance of complex systems. Exploiting the current trend towards sharing we want to initiate a collective movement that works towards creating synergies and harmonisation among different annotation efforts that are now dispersed. In this paper we present the general architecture of the Language Library, an initiative which is conceived as a facility for gathering and making available through simple functionalities the linguistic knowledge the field is able to produce, putting in place new ways of collaboration within the LRT community. In order to reach this goal, a first population round of the Language Library has started around a core of parallel/comparable texts that have been annotated by several contributors submitting a paper for LREC2012. The Language Library has also an ancillary aim related to language documentation and archiving and it is conceived as a theory-neutral space which allows for several language processing philosophies to coexist.}, KEYWORDS = {annotation, metadata, scientific crowdsourcing}, PAGES = {43-49}, URL = {https://publications.cnr.it/doc/220182}, CONFERENCE_NAME = {The Eight International Conference on Language Resources and Evaluation (LREC'12)}, CONFERENCE_PLACE = {Istanbul, Turkey}, CONFERENCE_DATE = {23-25 may 2012}, } @INPROCEEDINGS{SORIA_2012_INPROCEEDINGS_SBCMMOPQC_219679, AUTHOR = {Soria, C. and Bel, N. and Choukri, K. and Mariani, J. and Monachini, M. and Odijk, J. and Piperidis, S. and Quochi, V. and Calzolari, N.}, TITLE = {The FLaReNet Strategic Language Resource Agenda}, YEAR = {2012}, ABSTRACT = {The FLaReNet Strategic Agenda highlights the most pressing needs for the sector of Language Resources and Technologies and presents a set of recommendations for its development and progress in Europe, as issued from a three-year consultation of the FLaReNet European project. The FLaReNet recommendations are organised around nine dimensions: a) documentation b) interoperability c) availability, sharing and distribution d) coverage, quality and adequacy e) sustainability f) recognition g) development h) infrastructure and i) international cooperation. As such, they cover a broad range of topics and activities, spanning over production and use of language resources, licensing, maintenance and preservation issues, infrastructures for language resources, resource identification and sharing, evaluation and validation, interoperability and policy issues. The intended recipients belong to a large set of players and stakeholders in Language Resources and Technology, ranging from individuals to research and education institutions, to policy-makers, funding agencies, SMEs and large companies, service and media providers. The main goal of these recommendations is to serve as an instrument to support stakeholders in planning for and addressing the urgencies of the Language Resources and Technologies of the future.}, KEYWORDS = {strategic agenda, language resources planning, recommended priority actions}, PAGES = {1379-1386}, URL = {http://www.lrec-conf.org/proceedings/lrec2012/index.html}, ISBN = {978-2-9517408-7-7}, CONFERENCE_NAME = {The Eight International Conference on Language Resources and Evaluation (LREC'12)}, CONFERENCE_PLACE = {Istanbul, Turkey}, CONFERENCE_DATE = {23-25 may 2012}, BOOKTITLE = {Proceedings of the 8th international conference on Language Resources and Evaluation (LREC2012)}, EDITOR = {Calzolari, N. and Choukri, K. and Declerck, T. and Dogan, M. U. and Maegaard, B. and Mariani, J. and Odijk, J. and Piperidis, S.}, } @TECHREPORT{CALZOLARI_2012_TECHREPORT_C_288663, AUTHOR = {Calzolari, N.}, TITLE = {Multilingual Semantic Web and the challenges of Open Language Data}, YEAR = {2012}, ABSTRACT = {Language Technology (LT) is a data-intensive field and major breakthroughs have stemmed from a better use of more and more Language Resources (LRs). LRs and Open/Shared Language Data is therefore a great topic! New approaches are needed, both for Data and Meta-Data (LRs and Meta- LRs). My topics are linked to the layer of LRs and language services that serve LT, and especially open information on LRs and on research results. How can Linked Data contribute?}, KEYWORDS = {Language Resources (LRs)}, PAGES = {28-30}, URL = {http://drops.dagstuhl.de/opus/volltexte/2013/3788/pdf/dagrep_v002_i009_p015_s12362.pdf}, DOI = {10.4230/DagRep.2.9.15}, } @ARTICLE{THOMPSON_2011_ARTICLE_TMMCDLMMPQRSVRA_205232, AUTHOR = {Thompson, P. and McNaught, J. and Montemagni, S. and Calzolari, N. and Del Gratta, R. and Lee, V. and Marchi, S. and Monachini, M. and Pezik, P. and Quochi, V. and Rupp, C. and Sasaki, Y. and Venturi, G. and Rebholz Schuhmann, D. and Ananiadou, S.}, TITLE = {The BioLexicon: a large-scale terminological resource for biomedical text mining}, YEAR = {2011}, ABSTRACT = {Background Due to the rapidly expanding body of biomedical literature, biologists require increasingly sophisticated and efficient systems to help them to search for relevant information. Such systems should account for the multiple written variants used to represent biomedical concepts, and allow the user to search for specific pieces of knowledge (or events) involving these concepts, e.g., protein-protein interactions. Such functionality requires access to detailed information about words used in the biomedical literature. Existing databases and ontologies often have a specific focus and are oriented towards human use. Consequently, biological knowledge is dispersed amongst many resources, which often do not attempt to account for the large and frequently changing set of variants that appear in the literature. Additionally, such resources typically do not provide information about how terms relate to each other in texts to describe events. Results This article provides an overview of the design, construction and evaluation of a large-scale lexical and conceptual resource for the biomedical domain, the BioLexicon. The resource can be exploited by text mining tools at several levels, e.g., part-of-speech tagging, recognition of biomedical entities, and the extraction of events in which they are involved. As such, the BioLexicon must account for real usage of words in biomedical texts. In particular, the BioLexicon gathers together different types of terms from several existing data resources into a single, unified repository, and augments them with new term variants automatically extracted from biomedical literature. Extraction of events is facilitated through the inclusion of biologically pertinent verbs (around which events are typically organized) together with information about typical patterns of grammatical and semantic behaviour, which are acquired from domain-specific texts. In order to foster interoperability, the BioLexicon is modelled using the Lexical Markup Framework, an ISO standard. Conclusions The BioLexicon contains over 2.2 M lexical entries and over 1.8 M terminological variants, as well as over 3.3 M semantic relations, including over 2 M synonymy relations. Its exploitation can benefit both application developers and users. We demonstrate some such benefits by describing integration of the resource into a number of different tools, and evaluating improvements in performance that this can bring.}, KEYWORDS = {Text Mining, Information Extraction, Computational Lexicon}, PAGES = {1-29}, URL = {http://www.biomedcentral.com/1471-2105/12/397}, VOLUME = {12}, DOI = {10.1186/1471-2105-12-397}, PUBLISHER = {BioMed Central ([London], Regno Unito)}, ISSN = {1471-2105}, JOURNAL = {BMC bioinformatics}, } @INCOLLECTION{CALZOLARI_2011_INCOLLECTION_C_322399, AUTHOR = {Calzolari, N.}, TITLE = {Linguistica Computazionale e Risorse Linguistiche}, YEAR = {2011}, ABSTRACT = {A partire dagli anni '80 le cosiddette Risorse Linguistiche (RL) hanno progressivamente acquisito un ruolo sempre più importan­ te nella linguistica computazionale e nel Trattamento Automatico della Lingua (TAL). Questo processo è iniziato con il diffondersi degli approcci data-driven , all'interno dei quali le RL hanno con­ tribuito in modo decisivo allo sviluppo di sistemi innovativi e so­ prattutto "robusti", cioè in grado di trattare i fenomeni reali della lingua così come usata dai parlanti piuttosto che i fenomeni ritenuti "interessanti" dal linguista. Si è cominciato allora a riconoscere il ruolo infrastrutturale delle RL: Antonio Zampolli è stato il primo a comprendere questo ruolo e a lui dobbiamo anche l'introduzione del termine stesso "risorse linguistiche" ...}, KEYWORDS = {Linguistica Computazionale, Risorse Linguistiche RL, Standard}, PAGES = {32-64}, URL = {https://publications.cnr.it/doc/322399}, PUBLISHER = {Città Nuova (Roma, ITA)}, ISBN = {978-88-311-3505-4}, BOOKTITLE = {Scienze informatiche e biologiche. Epistemologia e ontologia}, EDITOR = {Cicchese, G. and Pettorossi, A. and Reghizzi, S. C. and Senni, V.}, } @INCOLLECTION{HAYASHI_2011_INCOLLECTION_HDCMSB_205409, AUTHOR = {Hayashi, Y. and Declerck, T. and Calzolari, N. and Monachini, M. and Soria, C. and Buitelaar, P.}, TITLE = {Language Service Ontology}, YEAR = {2011}, ABSTRACT = {The Language Grid is a distinctive language service infrastructure in the sense that it accommodates a wide variety of user needs, ranging from technical novices to experts; language resource consumers to language resource providers. As these language services are various in type and each of them can be idiosyncratic in many aspects, the service infrastructure has to address the issue of interoperability. A key to solve this issue is not only to build the services around standardized resources and interfaces, but also to establish a knowledge structure that copes effectively with a range of language services. Given this knowledge structure, referred to as a service ontology, each language service can be systematically classified and its usage specified by a corresponding API. This not only enables the utilization of existing language resources but facilitates the dissemination of newly created language resources as services.}, KEYWORDS = {Language grid, ontology}, PAGES = {85-100}, URL = {https://publications.cnr.it/doc/205409}, DOI = {10.1007/978-3-642-21178-2_6}, PUBLISHER = {Springer-Verlag (Berlin/Heidelberg, DEU)}, ISBN = {978-3-642-21177-5}, BOOKTITLE = {The Language Grid}, EDITOR = {Ishida, T.}, } @EDITORIAL{CALZOLARI_2011_EDITORIAL_CBSGMQ_206410, AUTHOR = {Calzolari, N. and Baroni, P. and Soria, C. and Goggi, S. and Monachini, M. and Quochi, V.}, TITLE = {Proceedings of the 3rd European Language Resources and Technologies Forum: Language Resources in the Sharing Age-the Strategic Agenda}, YEAR = {2011}, ABSTRACT = {Proceedings of the third FLaReNet forum on the European Language Resources and Technologies, held in Venezia, at the Auditorium Santa Margherita of the Università Ca' Foscari, on 26-27 May 2011.}, KEYWORDS = {Language Resources, Language Technologies}, PAGES = {86}, URL = {http://www.flarenet.eu/sites/default/files/FLaReNet_Forum_2011_Proceedings.pdf}, } @INPROCEEDINGS{CALZOLARI_2011_INPROCEEDINGS_CDFR_205564, AUTHOR = {Calzolari, N. and Del Gratta, R. and Frontini, F. and Russo, I.}, TITLE = {The Language Library: Many Layers, More Knowledge}, YEAR = {2011}, ABSTRACT = {In this paper we outline the general concept of the Language Library, a new initiative that has the purpose of building a huge archive of structured colletion of linguistic information. The Language Library is conceived as a community built repository and as an environment that allows language specialists to share multidimensional and multi-level annotated/processed resources. The first steps towards its implementation are briefly sketched.}, KEYWORDS = {Language Resources, Language Library}, PAGES = {93-97}, URL = {https://publications.cnr.it/doc/205564}, ISBN = {978-974-466-564-5}, CONFERENCE_NAME = {Workshop on Language Resources, Technology and Services in the Sharing Paradigm}, CONFERENCE_PLACE = {Chiang Mai}, CONFERENCE_DATE = {12 Novembre 2011}, } @INPROCEEDINGS{CALZOLARI_2011_INPROCEEDINGS_CIPS_288988, AUTHOR = {Calzolari, N. and Ishida, T. and Piperidis, S. and Sornlertlamvanich, V.}, TITLE = {Introduction}, YEAR = {2011}, ABSTRACT = {Some of the current major initiatives in the area of language resources - FLaReNet (http://www.flarenet.eu/), Language Grid (http://langrid.nict.go.jp/en/index.html) and META-SHARE (www.meta-share.org, www.meta-net.eu) - have agreed to organise a joint workshop on infrastructural issues that are critical in the age of data sharing and open data, to discuss the state of the art, international cooperation, future strategies and priorities, as well as the road-map of the area. It is an achievement, and an opportunity for our field, that recently a number of strategic-infrastructural initiatives have started all over the world. It is also a sign that funding agencies recognise the strategic value of our field and the importance of helping a coherent growth also through a number of coordinated actions. Some of these initiatives, two European and one Asian, have agreed to join forces to foster a debate that may lead to future coordinated actions all over the world. o}, KEYWORDS = {Language Resources and Technologies}, PAGES = {viii-ix}, URL = {https://publications.cnr.it/doc/288988}, CONFERENCE_NAME = {Workshop on Language Resources, Technology and Services in the Sharing Paradigm, IJCNLP 2011}, CONFERENCE_PLACE = {Chiang Mai, Thailand}, CONFERENCE_DATE = {November 12, 2011}, EDITOR = {Calzolari, N. and Ishida, T. and Piperidis, S. and Sornlertlamvanich, V.}, } @INPROCEEDINGS{CALZOLARI_2011_INPROCEEDINGS_CMQ_205719, AUTHOR = {Calzolari, N. and Monachini, M. and Quochi, V.}, TITLE = {Interoperability Framework: The FLaReNet action plan proposal}, YEAR = {2011}, ABSTRACT = {Standards are fundamental to ex-change, preserve, maintain and integrate data and language resources, and as an essential basis of any language resource infrastructure. This paper promotes an Interoperability Framework as a dynamic environment of standards and guidelines, also intended to support the provision of language-(web)service interoperability. In the past two decades, the need to define common practices and formats for linguistic resources has been increasingly recognized and sought. Today open, collaborative, shared data is at the core of a sound language strategy, and standardisation is actively on the move. This paper first describes the current landscape of standards, and presents the major barriers to their adoption; then, it describes those scenarios that critically involve the use of standards and provide a strong motivation for their adoption; lastly, a series of actions and steps needed to operationalise standards and achieve a full interoperability for Language Resources and Technologies are proposed.}, KEYWORDS = {Language Resources, standards}, PAGES = {41-49}, URL = {https://publications.cnr.it/doc/205719}, ISBN = {978-974-466-564-5}, CONFERENCE_NAME = {Workshop on Language Resources, Technology and Services in the Sharing Paradigm}, CONFERENCE_PLACE = {Chiang Mai}, CONFERENCE_DATE = {12 Novembre 2011}, } @TECHREPORT{BARONI_2011_TECHREPORT_BSC_206273, AUTHOR = {Baroni, P. and Soria, C. and Calzolari, N.}, TITLE = {The FLaReNet Databook}, YEAR = {2011}, ABSTRACT = {A collection of all the factual material collected during the activities of the FLaReNet project and a set of innovative initiatives and instruments that will remain in place for the continuous collection of such "facts". Editors: Paola Baroni, Claudia Soria, Nicoletta Calzolari. Contributors: Victoria Arranz, Núria Bel, Gerhard Budin, Tommaso Caselli, Khalid Choukri, Riccardo Del Gratta, Elina Desypri, Gil Francopoulo, Francesca Frontini, Sara Goggi, Olivier Hamon, Erhard Hinrichs, Penny Labropoulou, Lothar Lemnizer, Steven Krauwer, Valerie Mapelli, Joseph Mariani, Monica Monachini, Jan Odijk, Jungyeul Park, Stelios Piperidis, Adam Przepiorkowski, Valeria Quochi, Eva Revilla, Laurent Romary, Francesco Rubino, Irene Russo, Helmut Schmidt, Hans Uszkoreit, Peter Wittenburg.}, KEYWORDS = {Language Resources, Language Technologies}, URL = {http://www.flarenet.eu/sites/default/files/FLaReNet_Databook.pdf}, } @TECHREPORT{BARONI_2011_TECHREPORT_BSC_206324, AUTHOR = {Baroni, P. and Soria, C. and Calzolari, N.}, TITLE = {The FLaReNet Databook: http: //www. flarenet. eu/?q=FLaReNet_Databook}, YEAR = {2011}, ABSTRACT = {A collection of all the factual material collected during the activities of the FLaReNet project and a set of innovative initiatives and instruments that will remain in place for the continuous collection of such "facts". Editors: Paola Baroni, Claudia Soria, Nicoletta Calzolari. Contributors: Victoria Arranz, Núria Bel, Gerhard Budin, Tommaso Caselli, Khalid Choukri, Riccardo Del Gratta, Elina Desypri, Gil Francopoulo, Francesca Frontini, Sara Goggi, Olivier Hamon, Erhard Hinrichs, Penny Labropoulou, Lothar Lemnizer, Steven Krauwer, Valerie Mapelli, Joseph Mariani, Monica Monachini, Jan Odijk, Jungyeul Park, Stelios Piperidis, Adam Przepiorkowski, Valeria Quochi, Eva Revilla, Laurent Romary, Francesco Rubino, Irene Russo, Helmut Schmidt, Hans Uszkoreit, Peter Wittenburg.}, KEYWORDS = {Language Resources}, URL = {http://www.flarenet.eu/?q=FLaReNet_Databook}, } @TECHREPORT{CALZOLARI_2011_TECHREPORT_CBCMMOPQS_206397, AUTHOR = {Calzolari, N. and Bel, N. and Choukri, K. and Mariani, J. and Monachini, M. and Odijk, J. and Piperidis, S. and Quochi, V. and Soria, C.}, TITLE = {Final FLaReNet deliverable: Language Resources for the Future-The Future of Language Resources}, YEAR = {2011}, ABSTRACT = {Language Technologies (LT), together with their backbone, Language Resources (LR), provide an essential support to the challenge of Multilingualism and ICT of the future. The main task of language technologies is to bridge language barriers and to help creating a new environment where information flows smoothly across frontiers and languages, no matter the country, and the language, of origin. To achieve this goal, all players involved need to act as a community able to join forces on a set of shared priorities. However, until now the field of Language Resources and Technology has long suffered from an excess of individuality and fragmentation, with a lack of coherence concerning the priorities for the field, the direction to move, not to mention a common timeframe. The context encountered by the FLaReNet project was thus represented by an active field needing a coherence that can only be given by sharing common priorities and endeavours. FLaReNet has contributed to the creation of this coherence by gathering a wide community of experts and making them participate in the definition of an exhaustive set of recommendations.}, KEYWORDS = {language resources and technologies, infrastructures}, PAGES = {97}, URL = {https://publications.cnr.it/doc/206397}, } @TECHREPORT{CALZOLARI_2011_TECHREPORT_CQS_206420, AUTHOR = {Calzolari, N. and Quochi, V. and Soria, C.}, TITLE = {FLaReNet Strategic Language Resource Agenda}, YEAR = {2011}, ABSTRACT = {Despite the complexity of handling its languages, the European Union has established that cultural and language differences are a unique asset to be preserved. Europe needs to find means - such as technological ones - to overcome the language barriers to support citizens and industry in a multilingual globalised world. The large majority of industrial technological applications that handle natural language, i.e. Machine Translation, Crosslingual Information Retrieval, Multilingual Information Extraction, Automatic Document Indexing, Question Answering, Natural Language Interfaces, etc., include Language Resources as critical components. Although Language Technologies may consist of language independent engines, they depend on the availability of language-dependent knowledge under the form of Language Resources for their real-life implementation. At the same time, it is proved that a critical mass of Language Resources can make advancement in research and technology development possible and quicker, making Europe the leader of the market related to multilingualism. Companies such as Google or Microsoft play a dominant role in this framework, as they have access to a huge amount of data in many different languages, devote considerable resources to Language Technologies, have massive computing power and a direct research-to-application pipeline using a new business model based on so-called "free" services. The fact that a US company like Google is delivering some of the most comprehensive Language Technology solutions to support multilingualism should raise concern among EU officials.}, KEYWORDS = {Language resources, infrastructures}, PAGES = {23}, URL = {https://publications.cnr.it/doc/206420}, } @TECHREPORT{CALZOLARI_2011_TECHREPORT_CSBG_206274, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Goggi, S.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Final Report}, YEAR = {2011}, ABSTRACT = {Final report of the FLaReNet project.}, KEYWORDS = {Language Resources}, URL = {http://www.flarenet.eu/sites/default/files/D1.15.pdf}, } @TECHREPORT{CALZOLARI_2011_TECHREPORT_CSBCMOPB_206254, AUTHOR = {Calzolari, N. and Soria, C. and Bel, N. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S. and Baroni, P.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Progress Report No. 5}, YEAR = {2011}, ABSTRACT = {Fifth semestrial report on the progress of the FLaReNet project.}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/206254}, } @TECHREPORT{CALZOLARI_2011_TECHREPORT_CSBCMOPBG_206276, AUTHOR = {Calzolari, N. and Soria, C. and Bel, N. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S. and Baroni, P. and Goggi, S.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Progress Report No. 6}, YEAR = {2011}, ABSTRACT = {Sixth semestrial report on the progress of the FLaReNet project.}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/206276}, } @TECHREPORT{MONACHINI_2011_TECHREPORT_MQCBBCCFHKLMOPPRSUW_206507, AUTHOR = {Monachini, M. and Quochi, V. and Calzolari, N. and Bel, N. and Budin, G. and Caselli, T. and Choukri, K. and Francopoulo, G. and Hinrichs, E. and Krauwer, S. and Lemnitzer, L. and Mariani, J. and Odijk, J. and Piperidis, S. and Przepiorkowski, A. and Romary, L. and Schmidt, H. and Uszkoreit, H. and Wittenburg, P.}, TITLE = {The Standards' Landscape Towards an Interoperability Framework}, YEAR = {2011}, ABSTRACT = {This document proposes an overview of the current scene towards an Interoperability Framework and acts as a reference point for the current standards that the community fosters and encourages to adopt/improve. This initiative is in close synchronization with other relevant initiatives such as CLARIN, ELRA, ISO and TEI and META-Share. The document builds on the CLARIN Standardisation Action Plan and adapts and extends it to the needs of the broader LT Community, beyond the SSH research areas including the industry. The main goal of this document is to give a practical orientation for various LT players, both commercial and academic; the main message being that a harmonized domain of language resources and technology can be achieved stepwise, but that an effort to adopt standards is necessary to overcome fragmentation. NB: This is to be intended by no means as a static, closed document, rather a dynamic one which needs to be constantly/periodically revised and updated by the community itself.}, KEYWORDS = {Standards, interoperability}, PAGES = {23}, URL = {https://publications.cnr.it/doc/206507}, } @TECHREPORT{SORIA_2011_TECHREPORT_SC_206389, AUTHOR = {Soria, C. and Calzolari, N.}, TITLE = {Project presentation-results}, YEAR = {2011}, ABSTRACT = {International cooperation and re-creation of a community are the most important drivers for a coherent evolution of the Language Resource (LR) area in the next years. FLaReNet has been a European forum to facilitate interaction among LR stakeholders and its structure took into account the fact that LRs present various dimensions and must be approached from many perspectives: technical, but also organisational, economic, legal, political. The Network addressed also multicultural and multilingual aspects, essential when facing access and use of digital content in today's Europe. FLaReNet consolidated existing knowledge, presenting it analytically and visibly, and contributed to structuring the area of LRs of the future by discussing new strategies to: convert existing and experimental technologies related to LRs into useful economic and societal benefits; integrate so far partial solutions into broader infrastructures; consolidate areas mature enough for recommendation of best practices; anticipate the needs of new types of LRs. The outcomes of FLaReNet has been of a directive nature, to help identify those priority areas of LRs of major interest for the public that need public funding to develop or improve. A blueprint of actions has constituted the input to policy development both at EU and national level for identifying new language policies that support linguistic diversity in Europe, in combination with strengthening the language product market, e.g. for new products and innovative services, especially for less technologically advanced languages.}, KEYWORDS = {Language resources, infrastructures, international cooperation}, PAGES = {44}, URL = {https://publications.cnr.it/doc/206389}, } @ARTICLE{CALZOLARI_2010_ARTICLE_C_64554, AUTHOR = {Calzolari, N.}, TITLE = {FLaReNet-META-NET-CLARIN. La presenza Italiana nei più importanti progetti strategici e infrastrutturali di TAL in Europa}, YEAR = {2010}, ABSTRACT = {-}, KEYWORDS = {Trattamento Automatico della Lingua. Progetti Europei}, URL = {https://publications.cnr.it/doc/64554}, VOLUME = {Media}, } @ARTICLE{CALZOLARI_2010_ARTICLE_CI_30890, AUTHOR = {Calzolari, N. and Ide, N.}, TITLE = {LREC 2008: Selected Papers}, YEAR = {2010}, ABSTRACT = {Volume 44 marks the fifth year of the journal Language Resources and Evaluation, which in 2005 replaced Computers and the Humanities in both name and focus. At that time, especially in the light of the enormous success of the Language Resources and Evaluation Conference (LREC) that began in 1998, it seemed clear that the field lacked a journal dedicated to articles focused on resource creation, annotation, and evaluation. LRE was established to fill that gap. Since then, the journal's success has been literally overwhelming: since May 2005, 361 manuscripts have been submitted to the journal, of which 102 were eventually accepted for publication either as full journal papers or short notes. Many articles went through one or more iterations of revision in response to reviewer comments and resubmission before final acceptance. As a result of the efforts of both reviewers and authors, LRE is now regarded as one of the most highly respected journals in the field.}, KEYWORDS = {Language Resources and Evaluation}, PAGES = {181-293}, URL = {https://publications.cnr.it/doc/30890}, VOLUME = {44}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @ARTICLE{CALZOLARI_2010_ARTICLE_CSD_112952, AUTHOR = {Calzolari, N. and Soria, C. and Del Gratta, R.}, TITLE = {The LREC 2010 Map of Language Resources and Tools}, YEAR = {2010}, KEYWORDS = {Linguistic Tools. Language Resources}, URL = {https://publications.cnr.it/doc/112952}, } @INCOLLECTION{CALZOLARI_2010_INCOLLECTION_CS_30886, AUTHOR = {Calzolari, N. and Soria, C.}, TITLE = {Planning the Future of Language Resources: The Role of the FLaReNet Network}, YEAR = {2010}, ABSTRACT = {In this paper we analyse the role of Language Resources (LR) and Language Technologies (LT) in today Human Language Technology field and try to speculate on some of the priorities for the next years, from the particular perspective of the FLaReNet project, that has been asked to act as an observatory to assess current status of the field on Language Resources and Technology and to indicate priorities of action for the future.}, KEYWORDS = {Language Resources and Technology, strategic initiatives, priorities}, PAGES = {1-11}, URL = {https://rdcu.be/dfs8V}, VOLUME = {6008}, DOI = {10.1007/978-3-642-12116-6_1}, PUBLISHER = {Springer (Berlin, DEU)}, ISBN = {978-3-642-12116-6}, BOOKTITLE = {Computational Linguistics and Intelligent Text Processing. CICLing 2010}, EDITOR = {Gelbukh, A.}, } @INCOLLECTION{OLTRAMARI_2010_INCOLLECTION_OGHCLP_136475, AUTHOR = {Oltramari, A. and Gangemi, A. and Huang, C. and Calzolari, N. and Lenci, A. and Prévot, L.}, TITLE = {Synergizing ontologies and the lexicon: a roadmap}, YEAR = {2010}, KEYWORDS = {Ontology}, URL = {https://publications.cnr.it/doc/136475}, PUBLISHER = {Cambridge University Press (Cambridge, GBR)}, } @INCOLLECTION{PRVOT_2010_INCOLLECTION_PHCGLO_136467, AUTHOR = {Prévot, L. and Huang, C. and Calzolari, N. and Gangemi, A. and Lenci, A. and Oltramari, A.}, TITLE = {Ontology and the Lexicon: A Multidisciplinary Perspective}, YEAR = {2010}, ABSTRACT = {The relation between ontologies and language is currently at the forefront of natural language processing (NLP). Ontologies, as widely used models in semantic technologies, have much in common with the lexicon. A lexicon organizes words as a conventional inventory of concepts, while an ontology formalizes concepts and their logical relations. A shared lexicon is the prerequisite for knowledge-sharing through language, and a shared ontology is the prerequisite for knowledge-sharing through information technology. In building models of language, computational linguists must be able to accurately map the relations between words and the concepts that they can be linked to. This book focuses on the technology involved in enabling integration between lexical resources and semantic technologies. It will be of interest to researchers and graduate students in NLP, computational linguistics, and knowledge engineering, as well as in semantics, psycholinguistics, lexicology and morphology/syntax.}, KEYWORDS = {Ontology. Computational Lexicology}, PAGES = {3-24}, URL = {https://publications.cnr.it/doc/136467}, PUBLISHER = {Cambridge University Press (Cambridge, GBR)}, ISBN = {978-0-521-88659-8}, BOOKTITLE = {Ontology and the Lexicon: A Natural Language Processing Perspective}, EDITOR = {Huang, C. and Calzolari, N. and Gangenimi, A. and Lenci, A. and Oltramari, A. and Prévot, L.}, } @INCOLLECTION{RONZANO_2010_INCOLLECTION_RMMTC_169862, AUTHOR = {Ronzano, F. and Monachini, M. and Marchetti, A. and Tesconi, M. and Calzolari, N.}, TITLE = {Bootstrapping and Collaboratively Enriching the Italian Domain WordNet through the WiKyoto Knowledge Editor}, YEAR = {2010}, ABSTRACT = {Enhancing the development of multilingual resources is of utmost importance for use in computer applications. The need of ever growing resources for effective multilingual content processing has given impulse to a radical change in the perspective of language resource (LR) creation, structuring, exploitation and maintenance. The Web has played a key role in this process: indeed the possibility to access growing amounts of structured and unstructured data as well as the ease of creating and sharing contents between distributed communities of users have strongly affected the methodologies and techniques to bootstrap, enrich and access LRs. From static knowledge bases usually created and maintained by groups of experts and tailored to the specific exploitation contexts, LRs have turned into dynamic repositories of linguistic knowledge. Their content is usually easily accessible over the Web and often exploited aggregated and optimized on-the-fly by on-line information mining services. In this context, the adoption of standardized data formats to facilitate interoperability and data exchange is essential. Moreover, the creation and maintenance of these resources has taken great advantage from the possibility to harvest Web data in order to bootstrap or enrich them. Several new frameworks have been proposed to support access, search, integration and interoperability of "new generation" LRs. Wide distributed communities of Web users are more and more directly or indirectly involved in keeping language resources updated or in extending them. After a brief description of modern LRs, we focus our attention on two essential issues involving them: the need for standard formats that support interoperability in a distributed Web context and the possibility for the Web communities to collaboratively maintain and enrich these resources. In particular, we present the Italian WordNet (IWN) and its exploitation in the context of the KYOTO Project, as a real-world scenario where standardization, interlinking, enrichment as well as collaborative editing are put into practice.}, KEYWORDS = {NLP, collaborative editing, wordnet, knowledge representation, wiki}, PAGES = {181-208}, URL = {http://www.racai.ro/Multilinguality%20and%20Interoperability/TOC.html}, PUBLISHER = {Romanian Academy Publishing House (Bucharest, ROU)}, ISBN = {978-973-27-1972-5}, BOOKTITLE = {Multilinguality and Interoperability in Language Processing with Emphasis on Romanian}, EDITOR = {Tufis, D. and Forascu, I.}, } @EDITORIAL{CALZOLARI_2010_EDITORIAL_CBMS_136417, AUTHOR = {Calzolari, N. and Baroni, P. and Monachini, M. and Soria, C.}, TITLE = {Proceedings of the 2nd European Language Resources and Technologies Forum: Language Resources of the future-the future of Language Resources}, YEAR = {2010}, ABSTRACT = {Proceedings of the second FLaReNet forum on the European Language Resources and Technologies, held in Barcelona, at the Institut d'Estudis Catalans, on 11-12 February 2010.}, KEYWORDS = {Language Resources, Language Technologies, Future}, PAGES = {120}, URL = {http://www.flarenet.eu/sites/default/files/FLaReNet_Forum_2010_Proceedings.pdf}, } @EDITORIAL{CALZOLARI_2010_EDITORIAL_CCMMOPRT_136478, AUTHOR = {Calzolari, N. and Choukri, K. and Maegaard, B. and Mariani, J. and Odjik, J. and Piperidis, S. and Rosner, M. and Tapias, D.}, TITLE = {Seventh International Conference on Language Resources and Evaluation}, YEAR = {2010}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/136478}, } @EDITORIAL{HUANG_2010_EDITORIAL_HCGLO_157484, AUTHOR = {Huang, C. and Calzolari, N. and Gangemi, A. and Lenci, A. and Oltramari, A.}, TITLE = {Ontology and the lexicon: a natural language processing perspective}, YEAR = {2010}, KEYWORDS = {Ontology}, PAGES = {339}, URL = {http://www.cambridge.org/br/academic/subjects/languages-linguistics/computational-linguistics/ontology-and-lexicon-natural-language-processing-perspective}, PUBLISHER = {Cambridge University Press (Cambridge, GBR)}, ISBN = {9780521886598}, } @EDITORIAL{HUANG_2010_EDITORIAL_HCCGLOP_288563, AUTHOR = {Huang and Chu Ren and Calzolari, N. and Gangemi, A. and Lenci, A. and Oltramari, A. and Prévot, L.}, TITLE = {Ontology and the Lexicon: A Natural Language Processing Perspective}, YEAR = {2010}, ABSTRACT = {The relation between ontologies and language is at the forefront of both natural language processing (NLP) and knowledge engineering. Ontologies, as widely used models in semantic technologies, have much in common with the lexicon. A lexicon organizes words as a conventional inventory of concepts, while an ontology formalizes concepts and their logical relations. A shared lexicon is the prerequisite for knowledge-sharing through language, and a shared ontology is the prerequisite for knowledge-sharing through information technology. In building models of language, computational linguists must be able to map accurately the relations between words and the concepts that they can be linked to. This book focuses on the integration of lexical resources and semantic technologies. It will be of interest to researchers and graduate students in NLP, computational linguistics and knowledge engineering, as well as in semantics, psycholinguistics, lexicology and morphology/syntax. CHU-REN HUANG is Chair Professor in the Department of Chinese and Bilingual Studies at the Hong Kong Polytechnic University, and Research Fellow at the Institute of Linguistics, Academia Sinica in Taiwan. NICOLETTA CALZOLARI is Director of Research in Istituto di Linguistica Computazionale at the CNR in Italy. ALDO GANGEMI is senior researcher at the Institute of Cognitive Science and Technology of CNR (Italy), and coordinator of the Semantic Technology Lab. ALESSANDRO LENCI is a researcher in the Department of Linguistics at the University of Pisa. ALESSANDRO OLTRAMARI is a Research Fellow in the Laboratory for Applied Ontology, Institute of Cognitive Science and Technology at the Italian National Research Council. LAURENT PRÉVOT is an Associate Professor at the Université de Provence.}, KEYWORDS = {Knowledge engineering, Natural Language Processing. Ontology}, PAGES = {1-335}, URL = {https://publications.cnr.it/doc/288563}, PUBLISHER = {Cambridge university press (Cambridge, GBR)}, ISBN = {978-0-521-88659-8}, } @INPROCEEDINGS{CALZOLARI_2010_INPROCEEDINGS_C_84767, AUTHOR = {Calzolari, N.}, TITLE = {Introduction of the LREC 2010 Conference Chair}, YEAR = {2010}, KEYWORDS = {Language Resources and Evaluation}, URL = {https://publications.cnr.it/doc/84767}, CONFERENCE_NAME = {7th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Malta}, CONFERENCE_DATE = {2010}, } @INPROCEEDINGS{CALZOLARI_2010_INPROCEEDINGS_CS_84792, AUTHOR = {Calzolari, N. and Soria, C.}, TITLE = {Preparing the field for an Open Resource Infrastructure: the role of the FLaReNet Network of Excellence}, YEAR = {2010}, ABSTRACT = {In order to overcome the fragmentation that affects the field of Language Resources and Technologies, an Open and Distributed Resource Infrastructure is the necessary step for building on each other achievements, integrating resources and technologies and avoiding dispersed or conflicting efforts. Since this endeavour represents a true cultural turnpoint in the LRs field, it needs a careful preparation, both in terms of acceptance by the community and thoughtful investigation of the various technical, organisational and practical aspects implied. To achieve this, we need to act as a community able to join forces on a set of shared priorities and we need to act at a worldwide level. FLaReNet - Fostering Language Resources Network - is a Thematic Network funded under the EU eContent program that aims at developing the needed common vision and fostering a European and International strategy for consolidating the sector, thus enhancing competitiveness at EU level and worldwide. In this paper we present the activities undertaken by FLaReNet in order to prepare and support the establishment of such an Infrastructure, which is becoming now a reality within the new MetaNet initiative.}, KEYWORDS = {LR Infrastructures and Architectures, LR national/international projects, organizational/policy issues}, PAGES = {1295-1300}, URL = {https://publications.cnr.it/doc/84792}, PUBLISHER = {European Language Resources Association (ELRA)-Evaluations and Language resources Distribution Agency (ELDA) (Paris, FRA)}, ISBN = {2-9517408-6-7}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {19-21/05/2010}, BOOKTITLE = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)}, EDITOR = {Calzolari, N. and Choukri, K. and Maegaard, B. and Mariani, J. and Odijk, J. and Piperidis, S. and Rosner, M. and Tapias, D.}, } @INPROCEEDINGS{CALZOLARI_2010_INPROCEEDINGS_CSDGQRCMP_84809, AUTHOR = {Calzolari, N. and Soria, C. and Del Gratta, R. and Goggi, S. and Quochi, V. and Russo, I. and Choukri, K. and Mariani, J. and Piperidis, S.}, TITLE = {The LREC Map of Language Resources and Technologies}, YEAR = {2010}, ABSTRACT = {In this paper we present the LREC Map of Language Resources (data and tools), an innovative feature introduced in conjunction with the LREC 2010 Conference. The purpose of the Map is to shed light on the vast amount of resources that represent the background of the research presented at LREC, in the attempt to fill in a gap in the community knowledge about the resources that are used or created worldwide. It also aims at a change of culture in the field, actively engaging each researcher in the documentation task about resources. The Map has been developed on the basis of the information provided by LREC authors during the submission of papers to the LREC 2010 conference and the LREC workshops, and contains information about almost 2000 resources. The paper illustrates the motivation behind this initiative, its main characteristics, its relevance and future impact in the field, the metadata used to describe the resources, and finally presents some of the most relevant findings.}, KEYWORDS = {LR national/international projects, organizational/policy issues}, PAGES = {949-956}, URL = {http://www.lrec-conf.org/proceedings/lrec2010/index.html}, PUBLISHER = {European Language Resources Association (ELRA)-Evaluations and Language resources Distribution Agency (ELDA) (Paris, FRA)}, ISBN = {2-9517408-6-7}, CONFERENCE_NAME = {LREC 2010 Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {17-23 May 2010}, BOOKTITLE = {LREC'10-Seventh International Conference on Language Resources and Evaluation. Proceedings}, EDITOR = {Calzolari, N. and Choukri, K. and Maegaard, B. and Mariani, J. and Odjik, J. and Piperidis, S. and Rosner, M. and Tapias, D.}, } @INPROCEEDINGS{CIERI_2010_INPROCEEDINGS_CCCLLPIP_84788, AUTHOR = {Cieri, C. and Choukri, K. and Calzolari, N. and Langendoen, D. T. and Leveling, J. and Palmer, M. and Ide, N. and Pustejovsky, J.}, TITLE = {A Road Map for Interoperable Language Resource Metadata}, YEAR = {2010}, ABSTRACT = {LRs remain expensive to create and thus rare relative to demand across languages and technology types. The accidental re-creation of an LR that already exists is a nearly unforgiveable waste of scarce resources that is unfortunately not so easy to avoid. The number of catalogs the HLT researcher must search, with their different formats, make it possible to overlook an existing resource. This paper sketches the sources of this problem and outlines a proposal to rectify along with a new vision of LR cataloging that will to facilitates the documentation and exploitation of a much wider range of LRs than previously considered.}, KEYWORDS = {LR national/international projects, organizational/policy issues, LR Infrastructures and Architectures}, PAGES = {2506-2509}, URL = {https://publications.cnr.it/doc/84788}, PUBLISHER = {European Language Resources Association (ELRA)-Evaluations and Language resources Distribution Agency (ELDA) (Paris, FRA)}, ISBN = {2-9517408-6-7}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {17-23 May 2010}, } @INPROCEEDINGS{DELGRATTA_2010_INPROCEEDINGS_DDBCEMQSTC_84782, AUTHOR = {Del Gratta, R. and D'Onofrio, L. and Bartolini, R. and Caselli, T. and Enea, A. and Monachini, M. and Quochi, V. and Soria, C. and Toral, A. and Calzolari, N.}, TITLE = {A Web-based Architecture for Interoperability of Lexical Resources}, YEAR = {2010}, ABSTRACT = {In this paper we present aWeb Service Architecture for managing high level interoperability of Language Resources (LRs) by means of a Service Oriented Architecture (SOA) and the use of ISO standards, such as ISO LMF. We propose a layered architecture which separates the management of legacy resources (data collection) from data aggregation (workflow) and data access (user requests). We provide a case study to demonstrate how the proposed architecture is capable of managing data exchange among different lexical services in a coherent way and show how the use of a lexical standard becomes of primary importance when a protocol of interoperability is defined.}, KEYWORDS = {Interoperability, Web sercives, Lexical resources}, PAGES = {53-62}, URL = {http://weblab.iit.cnr.it/kyoto/www2.let.vu.nl/twiki/pub/Kyoto/Publications/icgl2010_DOnofrioetal.pdf}, PUBLISHER = {City university of Hong Kong press (Hong Kong, CHN)}, ISBN = {978-962-442-323-5}, CONFERENCE_NAME = {2nd International Conference on Global Interoperability for Language Resources}, CONFERENCE_PLACE = {Hong Kong}, CONFERENCE_DATE = {18-20 January 2010}, BOOKTITLE = {2nd International Conference on Global Interoperability for Language Resources, ICGL 2010}, EDITOR = {Fang, A. C. and Ide, N. and Webster, J.}, } @INPROCEEDINGS{SAVAS_2010_INPROCEEDINGS_SHMSC_84807, AUTHOR = {Savas, B. and Hayashi, Y. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {An LMF-based Web Service for Accessing WordNet-type Semantic Lexicons}, YEAR = {2010}, ABSTRACT = {This paper describes a Web service for accessing WordNet-type semantic lexicons. The central idea behind the service design is: given a query, the primary functionality of lexicon access is to present a partial lexicon by extracting the relevant part of the target lexicon. Based on this idea, we implemented the system as a RESTful Web service whose input query is specified by the access URI and whose output is presented in a standardized XML data format. LMF, an ISO standard for modeling lexicons, plays the most prominent role: the access URI pattern basically reflects the lexicon structure as defined by LMF; the access results are rendered based on Wordnet-LMF, which is a version of LMF XML-serialization. The Web service currently provides accesses to Princeton WordNet, Japanese WordNet, as well as the EDR Electronic Dictionary as a trial. To accommodate the EDR dictionary within the same framework, we modeled it also as a WordNet-type semantic lexicon. This paper thus propose modifications to LMF.}, KEYWORDS = {Standards for LRs, Lexicon, Lexical database, Web Services}, URL = {https://publications.cnr.it/doc/84807}, ISBN = {2-9517408-6-7}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {17-21/05/2010}, } @INPROCEEDINGS{WITTENBURG_2010_INPROCEEDINGS_WBBBCHKLMPPPSTVVW_84805, AUTHOR = {Wittenburg, P. and Bel, N. and Borin, L. and Budin, G. and Calzolari, N. and Hajicova, E. and Koskenniemi, K. and Lemnitzer, L. and Maegaard, B. and Piasecki, M. and Pierrel, J. and Piperidis, S. and Skadina, I. and Tufis, D. and Van Veenendaal, R. and Váradi, T. and Wynne, M.}, TITLE = {Resource and Service Centres as the Backbone for a Sustainable Service Infrastructure}, YEAR = {2010}, KEYWORDS = {LR Infrastructures and Architectures, Standards for LRs, Tools, Systerms, Applications}, URL = {https://publications.cnr.it/doc/84805}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {2010}, } @TECHREPORT{CALZOLARI_2010_TECHREPORT_CSB_157481, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Annual Report No. 2}, YEAR = {2010}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157481}, } @TECHREPORT{CALZOLARI_2010_TECHREPORT_CSBBBCMOP_157478, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Bel, N. and Budin, G. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Progress Report No. 3}, YEAR = {2010}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157478}, } @TECHREPORT{CALZOLARI_2010_TECHREPORT_CSBQBBCMOP_157488, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Quochi, V. and Bel, N. and Budin, G. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Progress Report No. 4}, YEAR = {2010}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157488}, } @ARTICLE{CALZOLARI_2009_ARTICLE_C_64544, AUTHOR = {Calzolari, N.}, TITLE = {FLaReNet: Shaping the Future of a Multilingual Digital Europe}, YEAR = {2009}, ABSTRACT = {The new EC eContentPlus Thematic Network (ECP-2007-LANG-617001) FLaReNet - Fostering Language Resources Network - aims at developing a common vision in the field of Language Resources (LRs) and Language Technologies (LTs) and fostering a European strategy for consolidating this area. the goal is to enhance competitiveness both in the EU and worldwide.}, KEYWORDS = {Language Resources and Language Technologies}, PAGES = {66-66}, URL = {https://publications.cnr.it/doc/64544}, VOLUME = {77}, } @ARTICLE{CALZOLARI_2009_ARTICLE_CB_172402, AUTHOR = {Calzolari, N. and Bel, N.}, TITLE = {FLaReNet: una red para fomentar los recursos lingüísticos (Fostering Language Resources Network: FLaReNet)}, YEAR = {2009}, ABSTRACT = {FLaReNet is a thematic network whose objective is the preparation of strategies and recommendations for the promotion and development of language technologies and the associated language resources because of their importance for minimizing the impact of the linguistic diversity in a digital and multilingual Europe. The results of this joint process of reflection by researchers and professionals of all around the world will be the basisi of European agreed policies for funding and promoting this sector.}, KEYWORDS = {Language Resources, Language Technology, Language Resources and Technology}, PAGES = {383-384}, URL = {https://publications.cnr.it/doc/172402}, VOLUME = {43}, } @ARTICLE{FRANCOPOULO_2009_ARTICLE_FBGCMPS_30882, AUTHOR = {Francopoulo, G. and Bel, N. and George, M. and Calzolari, N. and Monachini, M. and Pet, M. and Soria, C.}, TITLE = {Multilingual resources for NLP in the Lexical Markup Framework (LMF)}, YEAR = {2009}, ABSTRACT = {Optimizing the production, maintenance and extension of lexical resources is one the crucial aspects impacting Natural Language Processing (NLP). A second aspect involves optimizing the process leading to their integration in applications. With this respect, we believe that a consensual specification on monolingual, bilingual and multilingual lexicons can be a useful aid for the various NLP actors. Within ISO, one purpose of Lexical Markup Framework (LMF, ISO-24613) is to define a standard for lexicons that covers multilingual lexical data.}, KEYWORDS = {LMF, Standardization, ISO-TC37}, PAGES = {57-70}, URL = {https://publications.cnr.it/doc/30882}, VOLUME = {43}, DOI = {10.1007/s10579-008-9077-5}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @ARTICLE{QUOCHI_2009_ARTICLE_QDSBMC_30876, AUTHOR = {Quochi, V. and Del Gratta, R. and Sassolini, E. and Bartolini, R. and Monachini, M. and Calzolari, N.}, TITLE = {A Standard Lexical-Terminological Resource for the Bio Domain}, YEAR = {2009}, ABSTRACT = {The present paper describes a large-scale lexical resource for the biology domain designed both for human and for machine use. This lexicon aims at semantic interoperability and extendability, through the adoption of ISO-LMF standard for lexical representation and through a granular and distributed encoding of relevant information. The first part of this contribution focuses on three aspects of the model that are of particular interest to the biology community: the treatment of term variants, the representation on bio events and the alignment with a domain ontology. The second part of the paper describes the physical implementation of the model: a relational database equipped with a set of automatic uploading procedures. Peculiarity of the BioLexicon is that it combines features of both terminologies and lexicons. A set verbs relevant for the domain is also represented with full details on their syntactic and semantic argument structure.}, KEYWORDS = {Lexical representation model, Lexical Database, Computational Lexicography, Special Domains, Standards}, PAGES = {325-335}, URL = {https://publications.cnr.it/doc/30876}, VOLUME = {5603}, DOI = {10.1007/978-3-642-04235-5_28}, PUBLISHER = {Springer (Berlin, Germania)}, ISSN = {0302-9743}, JOURNAL = {Lecture notes in computer science}, } @ARTICLE{SORIA_2009_ARTICLE_SMBCHHMT_170611, AUTHOR = {Soria, C. and Monachini, M. and Bertagna, F. and Calzolari, N. and Huang, C. and Hsieh, S. and Marchetti, A. and Tesconi, M.}, TITLE = {Exploring Interoperability of Language Resources: the Case of Cross-lingual Semi-automatic Enrichment of Wordnets}, YEAR = {2009}, ABSTRACT = {In this paper we present an application fostering the integration and interoperability of computational lexicons, focusing on the particular case of mutual linking and cross-lingual enrichment of two wordnets, the ItalWordNet and Sinica BOW lexicons. This is intended as a case study investigating the needs and requirements of semi-automatic integration and interoperability of lexical resources, in the view of developing a prototype web application to support the GlobalWordNet Grid Initiative.}, KEYWORDS = {H. 3 INFORMATION STORAGE AND RETRIEVAL. Linguistic processing, Distributed language resources, Interoperable lexical resources, Language services}, PAGES = {87-96}, URL = {https://publications.cnr.it/doc/170611}, VOLUME = {43}, DOI = {10.1007/s10579-009-9082-3}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @INCOLLECTION{WITTENBURG_2009_INCOLLECTION_WAFC_157470, AUTHOR = {Wittenburg, P. and Arppe, A. and Forsstrom, P. and Calzolari, N.}, TITLE = {NEERI 09 Report}, YEAR = {2009}, KEYWORDS = {Interoperability}, URL = {https://publications.cnr.it/doc/157470}, } @EDITORIAL{CALZOLARI_2009_EDITORIAL_CBBBCGMMOPQST_183877, AUTHOR = {Calzolari, N. and Baroni, P. and Bel, N. and Budin, G. and Choukri, K. and Goggi, S. and Mariani, J. and Monachini, M. and Odijk, J. and Piperidis, S. and Quochi, V. and Soria, C. and Toral, A.}, TITLE = {Proceedings of the 1st European Language Resources and Technologies Forum: Shaping the Future of the Multilingual Digital Europe}, YEAR = {2009}, ABSTRACT = {Proceedings of the first FLaReNet Forum on the European Language Resources and Technologies, held in Vienna, at the Austrian Academy of Science, on 12-13 February 2009.}, KEYWORDS = {Language Resources, Language Technologies, Multilingual, Digital}, PAGES = {105}, URL = {http://www.flarenet.eu/sites/default/files/Vienna09_Proceedings.pdf}, } @INPROCEEDINGS{CALZOLARI_2009_INPROCEEDINGS_C_84744, AUTHOR = {Calzolari, N.}, TITLE = {Introduction by the FLaReNet Coordinator}, YEAR = {2009}, KEYWORDS = {Language Resources, Language Technologies}, URL = {https://publications.cnr.it/doc/84744}, CONFERENCE_NAME = {Fostering Language Resources Network Forum 2009}, CONFERENCE_PLACE = {Vienna}, CONFERENCE_DATE = {2009}, } @INPROCEEDINGS{CALZOLARI_2009_INPROCEEDINGS_CPR_84748, AUTHOR = {Calzolari, N. and Pustejovsky, J. and Rumshisky, A.}, TITLE = {Proceedings of the 5th International Conference on Generative Approaches to the Lexicon}, YEAR = {2009}, KEYWORDS = {Lexicon}, URL = {https://publications.cnr.it/doc/84748}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {2009}, } @INPROCEEDINGS{CALZOLARI_2009_INPROCEEDINGS_CS_84758, AUTHOR = {Calzolari, N. and Soria, C.}, TITLE = {The FLaReNet Thematic Network: a Global Forum for Cooperation}, YEAR = {2009}, KEYWORDS = {Language Resources, Language Technologies}, URL = {https://publications.cnr.it/doc/84758}, CONFERENCE_NAME = {ACL-IJCNLP 2009-7th Workshop on Asian Language Resources}, CONFERENCE_PLACE = {Suntec, Singapore}, CONFERENCE_DATE = {2009}, } @INPROCEEDINGS{IDE_2009_INPROCEEDINGS_IPCS_84760, AUTHOR = {Ide, N. and Pustejovsky, J. and Calzolari, N. and Soria, C.}, TITLE = {The SILT and FLaReNet International Collaboration for Interoperability}, YEAR = {2009}, KEYWORDS = {Interoperability, Language Resources, Language Technologies}, URL = {https://publications.cnr.it/doc/84760}, CONFERENCE_NAME = {ACL-IJCNLP 2009-3rd Linguistic Annotation Workshop}, CONFERENCE_PLACE = {Suntec, Singapore}, CONFERENCE_DATE = {2009}, } @INPROCEEDINGS{JEZEK_2009_INPROCEEDINGS_JQC_84752, AUTHOR = {Jezek, E. and Quochi, V. and Calzolari, N.}, TITLE = {Relevance of Qualia Relations in Coercive Contexts}, YEAR = {2009}, KEYWORDS = {annotation, annotation scheme, semantics, type shift}, URL = {https://publications.cnr.it/doc/84752}, CONFERENCE_NAME = {5th International Conference on Generative Approaches to the Lexicon}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {2009}, } @INPROCEEDINGS{TOKUNAGA_2009_INPROCEEDINGS_TKCMSSCTXHHK_84751, AUTHOR = {Tokunaga, T. and Kaplan, D. and Calzolari, N. and Monachini, M. and Soria, C. and Sornlertlamvanich, V. and Charoenporn, T. and Tesconi, M. and Xia, Y. and Huang, C. and Hsieh, S. and Kiyoaki, S.}, TITLE = {Query Expansion using LMF-Compliant Lexical Resources}, YEAR = {2009}, ABSTRACT = {This paper reports prototype multilingual query expansion system relying on LMF compliant lexical resources. The system is one of the deliverables of a three-year project aiming at establishing an international standard for language resources which is applicable to Asian languages. Our important contributions to ISO 24613, standard Lexical Markup Framework (LMF) include its robustness to deal with Asian languages, and its applicability to cross-lingual query tasks, as illustrated by the prototype introduced in this paper.}, KEYWORDS = {Lexical resources, Lexical Markup Framework (LMF), Standards}, PAGES = {145-152}, URL = {https://publications.cnr.it/doc/84751}, ISBN = {978-1-932432-56-5}, CONFERENCE_NAME = {ACL-IJCNLP 2009-7th Workshop on Asian Language Resources}, CONFERENCE_PLACE = {Singapore}, CONFERENCE_DATE = {6-7 Agosto 2009}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CBGMQST_157465, AUTHOR = {Calzolari, N. and Baroni, P. and Goggi, S. and Monachini, M. and Quochi, V. and Soria, C. and Toral, A.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Dissemination Plan}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157465}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CBGMQST_157468, AUTHOR = {Calzolari, N. and Baroni, P. and Goggi, S. and Monachini, M. and Quochi, V. and Soria, C. and Toral, A.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Progress Report No. 1}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157468}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CMSBGQT_157467, AUTHOR = {Calzolari, N. and Monachini, M. and Soria, C. and Baroni, P. and Goggi, S. and Quochi, V. and Toral, A.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Progress Report No. 2}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157467}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CSBCGMQTBBCMOP_157462, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Caselli, T. and Goggi, S. and Monachini, M. and Quochi, V. and Toral, A. and Bel, N. and Budin, G. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Action Plan}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157462}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CSBGMQT_157466, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Goggi, S. and Monachini, M. and Quochi, V. and Toral, A.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Evaluation Plan for the functioning of the Network}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157466}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CSBMQ_157463, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Monachini, M. and Quochi, V.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Annual Report No. 1}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157463}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CSBMQT_157469, AUTHOR = {Calzolari, N. and Soria, C. and Baroni, P. and Monachini, M. and Quochi, V. and Toral, A.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Project Presentation}, YEAR = {2009}, KEYWORDS = {Language Resources}, URL = {https://publications.cnr.it/doc/157469}, } @TECHREPORT{CALZOLARI_2009_TECHREPORT_CSBBCCMMOPQT_157464, AUTHOR = {Calzolari, N. and Soria, C. and Bel, N. and Budin, G. and Caselli, T. and Choukri, K. and Mariani, J. and Monachini, M. and Odijk, J. and Piperidis, S. and Quochi, V. and Toral, A.}, TITLE = {ECP-2007-LANG-617001 FLaReNet: Blueprint of actions and infrastructures No. 1}, YEAR = {2009}, KEYWORDS = {Language Resources, Infrastructures, Recommendations}, URL = {https://publications.cnr.it/doc/157464}, } @MISC{CALZOLARI_2009_MISC_CBBBCGMMOPQST_157471, AUTHOR = {Calzolari, N. and Baroni, P. and Bel, N. and Budin, G. and Choukri, K. and Goggi, S. and Mariani, J. and Monachini, M. and Odijk, J. and Piperidis, S. and Quochi, V. and Soria, C. and Toral, A.}, TITLE = {The European Language Resources and Technologies Forum: Shaping the Future of the Multilingual Digital Europe}, YEAR = {2009}, KEYWORDS = {Language Resources, Language Technologies}, URL = {https://publications.cnr.it/doc/157471}, } @MISC{CALZOLARI_2009_MISC_CBBCMOPBGMQST_157457, AUTHOR = {Calzolari, N. and Bel, N. and Budin, G. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S. and Baroni, P. and Goggi, S. and Monachini, M. and Quochi, V. and Soria, C. and Toral, A.}, TITLE = {Extended Report of: The European Language Resources and Technologies Forum: Shaping the Future of the Multilingual Digital Europe}, YEAR = {2009}, KEYWORDS = {Language Resources, Language Technologies}, URL = {https://publications.cnr.it/doc/157457}, } @MISC{CALZOLARI_2009_MISC_CBBCMOPBGMQST_157460, AUTHOR = {Calzolari, N. and Bel, N. and Budin, G. and Choukri, K. and Mariani, J. and Odijk, J. and Piperidis, S. and Baroni, P. and Goggi, S. and Monachini, M. and Quochi, V. and Soria, C. and Toral, A.}, TITLE = {Short Report of The European Language Resources and Technologies Forum: Shaping the Future of the Multilingual Digital Europe}, YEAR = {2009}, KEYWORDS = {Language Resources, Language Technologies}, URL = {https://publications.cnr.it/doc/157460}, } @ARTICLE{CALZOLARI_2008_ARTICLE_C_30875, AUTHOR = {Calzolari, N.}, TITLE = {Initiatives, Tendencies and Driving Forces for a 'Lexical Web' as Part of a 'Language Infrastructure'}, YEAR = {2008}, ABSTRACT = {While highlighting the infrastructural role of Language Resources (LR) I sketch my perception of the current situation in the LR field. I underline some of the priority areas of concern today with respect to implementing an open Language Infrastructure, and specifically what we could call a "Lexical Web". My objective is to show that it is imperative that there is an underlying global strategy behind the set of initiatives which are/can be launched in Europe and world-wide, and that a global vision and cooperation among different communities is necessary to achieve more coherent and useful results. I end up mentioning two new European initiatives that go on this direction and promise to be influential in shaping the future of the LR area.}, KEYWORDS = {Language Resources, Language Infrastructure, Computational Lexicons, Standards, Language Technology}, PAGES = {90-105}, URL = {http://www.springerlink.com/content/54357211172v7653/}, VOLUME = {4938}, DOI = {10.1007/978-3-540-78159-2_10}, PUBLISHER = {Springer (Berlin, Germania)}, ISSN = {0302-9743}, JOURNAL = {Lecture notes in computer science}, } @ARTICLE{CALZOLARI_2008_ARTICLE_C_64542, AUTHOR = {Calzolari, N.}, TITLE = {Language Infrastructures: what happens outside Europe?}, YEAR = {2008}, ABSTRACT = {The setup of CLARIN in Europe was the result of a long series of initiatives and attempts from many of us, starting already at the beginning on the 6th Framework Programme. That time is finally ripe for such an infrastructure is shown also by other initiatives outside Europe that share objectives and ideas with CLARIN. I mention here just a few.}, KEYWORDS = {Language Technology}, PAGES = {1-1}, URL = {https://publications.cnr.it/doc/64542}, VOLUME = {3}, } @ARTICLE{CALZOLARI_2008_ARTICLE_CC_288393, AUTHOR = {Calzolari, N. and Choukri, K.}, TITLE = {LREC2008-The Language Resources and Evaluation Conference}, YEAR = {2008}, ABSTRACT = {LREC, launched in 1998 in Granada as a visionary idea of Antonio Zampolli and other colleagues, celebrated its tenth birthday in the wonderful city of Marrakech. The conference had the honour of receiving the Royal Patronage of His Majesty Mohammed VI, King of Morocco, highlighting the importance assigned to multilingual and multicultural issues.}, KEYWORDS = {Language Resources}, PAGES = {56-56}, URL = {http://ercim-news.ercim.eu/images/stories/EN74/EN74-web.pdf}, VOLUME = {74 July 2008}, PUBLISHER = {ERCIM (Le Chesnay)}, ISSN = {0926-4981}, JOURNAL = {ERCIM news}, } @INPROCEEDINGS{BROEDER_2008_INPROCEEDINGS_BDHPRCW_84715, AUTHOR = {Broeder, D. and Declerck, T. and Hinrichs, E. and Piperidis, S. and Romary, L. and Calzolari, N. and Wittenburg, P.}, TITLE = {Foundation of a Component-based Flexible Registry for Language Resources and Technology}, YEAR = {2008}, KEYWORDS = {Metadata, Digital libraries, LR Infrastructures and Architectures}, URL = {https://publications.cnr.it/doc/84715}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {2008}, } @INPROCEEDINGS{CALZOLARI_2008_INPROCEEDINGS_C_84702, AUTHOR = {Calzolari, N.}, TITLE = {Approaches towards a Lexical Web: the role of Interoperability}, YEAR = {2008}, KEYWORDS = {Language Resources, Lexicons, Ontology}, URL = {https://publications.cnr.it/doc/84702}, CONFERENCE_NAME = {The First International Conference on Global Interoperability for Language Resources}, CONFERENCE_PLACE = {Hong Kong}, CONFERENCE_DATE = {2008}, } @INPROCEEDINGS{DELGRATTA_2008_INPROCEEDINGS_DBCMSC_84729, AUTHOR = {Del Gratta, R. and Bartolini, R. and Caselli, T. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {UFRA: a UIMA-based Approach to Federated Language Resource Architecture}, YEAR = {2008}, ABSTRACT = {In this paper we address the issue of developing an interoperable infrastructure for language resources and technologies. In our approach, called UFRA, we extend the Federate Database Architecture System adding typical functionalities caming from UIMA. In this way, we capitalize the advantages of a federated architecture, such as autonomy, heterogeneity and distribution of components, monitored by a central authority responsible for checking both the integration of components and user rights on performing different tasks. We use the UIMA approach to manage and define one common front-end, enabling users and clients to query, retrieve and use language resources and technologies. The purpose of this paper is to show how UIMA leads from a Federated Database Architecture to a Federated Resource Architecture, adding to a registry of available components both static resources such as lexicons and corpora and dynamic ones such as tools and general purpose language technologies. At the end of the paper, we present a case-study that adopts this framework to integrate the SIMPLE lexicon and TIMEML annotation guidelines to tag natural language texts.}, KEYWORDS = {LR Infrastructures and Architectures, LR web services, Lexicon, Lexical database}, PAGES = {2634-2639}, URL = {http://www.lrec-conf.org/proceedings/lrec2008/pdf/656_paper.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {26 May-1 June 2008}, } @INPROCEEDINGS{DELGRATTA_2008_INPROCEEDINGS_DCCR_84724, AUTHOR = {Del Gratta, R. and Caselli, T. and Calzolari, N. and Ruimy, N.}, TITLE = {TimeML: An ontological mapping onto UIMA Type Systems}, YEAR = {2008}, KEYWORDS = {Infrastructure, UIMA, Event detection}, URL = {https://publications.cnr.it/doc/84724}, CONFERENCE_NAME = {ICGL 2008, The First International Conference on Global Interoperability for Language Resources}, CONFERENCE_PLACE = {Hong Kong}, CONFERENCE_DATE = {2008}, } @INPROCEEDINGS{HAYASHI_2008_INPROCEEDINGS_HNMSC_84725, AUTHOR = {Hayashi, Y. and Narawa, C. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {Ontologizing Lexicon Access Functions based on an LMF-based Lexicon Taxonomy}, YEAR = {2008}, ABSTRACT = {This paper discusses ontologization of lexicon access functions in the context of a service-oriented language infrastructure, such as the Language Grid. In such a language infrastructure, an access function to a lexical resource, embodied as an atomic Web service, plays a crucially important role in composing a composite Web service tailored to a user's specific requirement. To facilitate the composition process involving service discovery, planning and invocation, the language infrastructure should be ontology-based; hence the ontologization of a range of lexicon functions is highly required. In a service-oriented environment, lexical resources however can be classified from a service-oriented perspective rather than from a lexicographically motivated standard. Hence to address the issue of interoperability, the taxonomy for lexical resources should be ground to principled and shared lexicon ontology. To do this, we have ontologized the standardized lexicon modeling framework LMF, and utilized it as a foundation to stipulate the service-oriented lexicon taxonomy and the corresponding ontology for lexicon access functions. This paper also examines a possible solution to fill the gap between the ontological descriptions and the actual Web service API by adopting a W3C recommendation SAWSDL, with which Web service descriptions can be linked with the domain ontology.}, KEYWORDS = {Lexicon, LR web services, Standards for LRs, Lexical database}, PAGES = {916-922}, URL = {https://publications.cnr.it/doc/84725}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {26-05/1-06-2008}, } @INPROCEEDINGS{MAGNINI_2008_INPROCEEDINGS_MCTBMLBCTBSS_92169, AUTHOR = {Magnini, B. and Cappelli, A. and Tamburini, F. and Bosco, C. and Mazzei, A. and Lombardo, V. and Bertagna, F. and Calzolari, N. and Toral, A. and Bartalesi, L. V. and Sprugnoli, R. and Speranza, M.}, TITLE = {Evaluation of natural language tools for italian: EVALITA 2007}, YEAR = {2008}, ABSTRACT = {EVALITA 2007, the first edition of the initiative devoted to the evaluation of Natural Language Processing tools for Italian, provided a shared framework where participants' systems had the possibility to be evaluated on five different tasks, namely Part of Speech Tagging (organised by the University of Bologna), Parsing (organised by the University of Torino), Word Sense Disambiguation (organised by CNR-ILC, Pisa), Temporal Expression Recognition and Normalization (organised by CELCT, Trento), and Named Entity Recognition (organised by FBK, Trento). We believe that the diffusion of shared tasks and shared evaluation practices is a crucial step towards the development of resources and tools for Natural Language Processing. Experiences of this kind, in fact, are a valuable contribution to the validation of existing models and data, allowing for consistent comparisons among approaches and among representation schemes. The good response obtained by EVALITA, both in the number of participants and in the quality of results, showed that pursuing such goals is feasible not only for English, but also for other languages.}, KEYWORDS = {Natural language evaluation, Standards for LRs, Evaluation methodologies}, PAGES = {2536-2543}, URL = {http://www.lrec-conf.org/proceedings/lrec2008/}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {Proceedings of LREC 2008}, CONFERENCE_PLACE = {Marrakech, Morocco}, CONFERENCE_DATE = {28-30 May 2008}, BOOKTITLE = {Proceeding LREC 2008}, EDITOR = {Calzolari, N. and Choukri, K. and Maegard, B.}, } @INPROCEEDINGS{MAGNINI_2008_INPROCEEDINGS_MCTBMLBCTBSS_171693, AUTHOR = {Magnini, B. and Cappelli, A. and Tamburini, F. and Bosco, C. and Mazzei, A. and Lombardo, V. and Bertagna, F. and Calzolari, N. and Toral, R. A. and Bartalesi, L. V. and Sprugnoli, R. and Speranza, M.}, TITLE = {Evaluation of natural language tools for italian: EVALITA 2007}, YEAR = {2008}, ABSTRACT = {EVALITA 2007, the first edition of the initiative devoted to the evaluation of Natural Language Processing tools for Italian, provided a shared framework where participants' systems had the possibility to be evaluated on five different tasks, namely Part of Speech Tagging (organised by the University of Bologna), Parsing (organised by the University of Torino), Word Sense Disambiguation (organised by CNR-ILC, Pisa), Temporal Expression Recognition and Normalization (organised by CELCT, Trento), and Named Entity Recognition (organised by FBK, Trento). We believe that the diffusion of shared tasks and shared evaluation practices is a crucial step towards the development of resources and tools for Natural Language Processing. Experiences of this kind, in fact, are a valuable contribution to the validation of existing models and data, allowing for consistent comparisons among approaches and among representation schemes. The good response obtained by EVALITA, both in the number of participants and in the quality of results, showed that pursuing such goals is feasible not only for English, but also for other languages.}, KEYWORDS = {Natural language evaluation, Standards for LRs, Evaluation methodologies, H. 3 INFORMATION STORAGE AND RETRIEVAL. Linguistic processing}, PAGES = {2536-2543}, URL = {https://publications.cnr.it/doc/171693}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {26th May-1st June 2008}, } @INPROCEEDINGS{MARCHETTI_2008_INPROCEEDINGS_MTVARCMFHIKNRV_173483, AUTHOR = {Marchetti, A. and Tesconi, M. and Vossen, P. and Agirre, E. and Rigau, G. and Calzolari, N. and Monachini, M. and Fellbaum, C. and Hsieh, S. and Isahara, H. and Kanzaki, K. and Neri, F. and Raffaelli, R. and Vangent, J.}, TITLE = {KYOTO: A System for Mining, Structuring, and Distributing Knowledge Across Languages and Cultures}, YEAR = {2008}, ABSTRACT = {We outline work to be carried out within the framework of an impending EC project. The goal is to construct a language-independent information system for a specific domain (environment/ecology) anchored in a language-independent ontology that is linked to WordNets in several languages. For each language, information extraction and identification of lexicalized concepts with ontological entries will be done by text miners ("Kybots"). The mapping of language-specific lexemes to the ontology allows for crosslinguistic identification and translation of equivalent terms. The infrastructure developed within this project will enable long-range knowledge sharing and transfer to many languages and cultures, addressing the need for global and uniform transition of knowledge beyond the domain of ecology and environment addressed here.}, KEYWORDS = {Global WordNet Grid, Ontologies and WordNets, Multilinguality, Semantic indexing and search, Text mining}, PAGES = {474-484}, URL = {https://publications.cnr.it/doc/173483}, ISBN = {978-963-482-854-9}, CONFERENCE_NAME = {GWC2008-The Fourth Global WordNet Conference}, CONFERENCE_PLACE = {Szeged, Hungary}, CONFERENCE_DATE = {22-25 Gennaio 2008}, EDITOR = {Tanács, A. and Csendes, D. and Vincze, V. and Fellbaum, C. and Vossen, P.}, } @INPROCEEDINGS{MONACHINI_2008_INPROCEEDINGS_MQDC_84731, AUTHOR = {Monachini, M. and Quochi, V. and Del Gratta, R. and Calzolari, N.}, TITLE = {Using LMF to Shape a Lexicon for the Biomedical Domain}, YEAR = {2008}, ABSTRACT = {This paper describes the design, implementation and population of the BioLexicon in the framework of BootStrep, an FP6 project. The BioLexicon (BL) is a lexical resource designed for text mining in the bio-domain. It has been conceived to meet both domain requirements and upcoming ISO standards for lexical representation. The data model and data categories are compliant to the ISO Lexical Markup Framework and the Data Category Registry. The BioLexicon integrates features of lexicons and terminologies: term entries (and variants) derived from existing resources are enriched with linguistic features, including sub-categorization and predicate-argument information, extracted from texts. Thus, it is an extendable resource. Furthermore, the lexical entries will be aligned to concepts in the BioOntology, the ontological resource of the project. The BL implementation is an extensible relational database with automatic population procedures. Population relies on a dedicated input data structure allowing to upload terms and their linguistic properties and "pull-and-push" them in the database. The BioLexicon teaches that the state-of-the-art is mature enough to aim at setting up a standard in this domain. Being conformant to lexical standards, the BioLexicon is interoperable and portable to other areas.}, KEYWORDS = {Domain terminologies, Computational lexicons, Lexical standards, Lexical architectures}, PAGES = {153-157}, URL = {https://publications.cnr.it/doc/84731}, CONFERENCE_NAME = {LangTech 2008-Tecnologia applicata alla linguistica}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {28-29 February 2008}, EDITOR = {Delogu, C. and Falcone, M.}, } @INPROCEEDINGS{QUOCHI_2008_INPROCEEDINGS_QMDC_84700, AUTHOR = {Quochi, V. and Monachini, M. and Del Gratta, R. and Calzolari, N.}, TITLE = {A lexicon for biology and bioinformatics: the BOOTStrep experience}, YEAR = {2008}, KEYWORDS = {Lexicon, Ontologies, Lexical database}, PAGES = {2285-2292}, URL = {http://www.lrec-conf.org/proceedings/lrec2008/pdf/576_paper.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {26-05/1-06-2008}, } @INPROCEEDINGS{TAKENOBU_2008_INPROCEEDINGS_TKHHCMSSSCY_84701, AUTHOR = {Takenobu, T. and Kaplan, D. and Huang, C. and Hsieh, S. and Calzolari, N. and Monachini, M. and Soria, C. and Shirai, K. and Sornlertlamvanich, V. and Charoenporn, T. and Yingju, X.}, TITLE = {Adapting International Standard for Asian Language Technologies}, YEAR = {2008}, ABSTRACT = {Corpus-based approaches and statistical approaches have been the main stream of natural language processing research for the past two decades. Language resources play a key role in such approaches, but there is an insufficient amount of language resources in many Asian languages. In this situation, standardisation of language resources would be of great help in developing resources in new languages. This paper presents the latest development efforts of our project which aims at creating a common standard for Asian language resources that is compatible with an international standard. In particular, the paper focuses on i) lexical specification and data categories relevant for building multilingual lexical resources for Asian languages; ii) a core upper-layer ontology needed for ensuring multilingual interoperability and iii) the evaluation platform used to test the entire architectural framework.}, KEYWORDS = {LR national/international projects, Organizational/policy issues, LR Infrastructures and Architectures, Lexicon, Lexical database}, PAGES = {1663}, URL = {http://www.lrec-conf.org/proceedings/lrec2008/pdf/422_paper.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Morocco}, CONFERENCE_DATE = {26-05/1-06-2008}, } @INPROCEEDINGS{TORAL_2008_INPROCEEDINGS_TQDMSC_84714, AUTHOR = {Toral, R. A. and Quochi, V. and Del Gratta, R. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {Lexically-based Ontologies and Ontologically Based Lexicons}, YEAR = {2008}, ABSTRACT = {This paper deals with the relations between ontologies and lexicons. We study the role of these two components and their evolution during the last years in the field of Computational Linguistics. Subsequently, we survey the current lines of research at ILC-CNR which tackle this topic. They involve (I) the reuse of already existing Lexical Resources to derive formal ontologies, (II) the conversion and combination of terminologies into rich and formal Lexical Resources and (III) the use of formal ontologies as the backbone of multilingual Lexical Resources.}, KEYWORDS = {Resource Infrastructure, UIMA, Clarin}, PAGES = {49-59}, URL = {https://publications.cnr.it/doc/84714}, CONFERENCE_NAME = {AI*IA 2008-10th Congress of Italian Association for Artificial Intelligence}, CONFERENCE_PLACE = {Cagliari}, CONFERENCE_DATE = {11-13 Settembre 2008}, } @INPROCEEDINGS{VOSSEN_2008_INPROCEEDINGS_VACFHHIKMMNRRTV_84716, AUTHOR = {Vossen, P. and Agirre, E. and Calzolari, N. and Fellbaum, C. and Hsieh, S. and Huang, C. and Isahara, H. and Kanzaki, K. and Marchetti, A. and Monachini, M. and Neri, F. and Raffaelli, R. and Rigau, G. and Tesconi, M. and Vangent, J.}, TITLE = {KYOTO: A System for Mining, Structuring, and Distributing Knowledge Across Languages and Cultures}, YEAR = {2008}, ABSTRACT = {We outline work performed within the framework of a current EC project. The goal is to construct a language-independent information system for a specific domain (environment/ecology/biodiversity) anchored in a language-independent ontology that is linked to wordnets in seven languages. For each language, information extraction and identification of lexicalized concepts with ontological entries is carried out by text miners ("Kybots"). The mapping of language-specific lexemes to the ontology allows for crosslinguistic identification and translation of equivalent terms. The infrastructure developed within this project enables long-range knowledge sharing and transfer across many languages and cultures, addressing the need for global and uniform transition of knowledge beyond the specific domains addressed here.}, KEYWORDS = {Information Extraction, Information Retrieval, Digital libraries, Lexicon, Lexical database}, URL = {https://publications.cnr.it/doc/84716}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {26-05/1-06-2008}, } @INPROCEEDINGS{CALZOLARI_2008_INPROCEEDINGS_C_112933, AUTHOR = {Calzolari, N.}, TITLE = {New European Infrastructural and Networking Initiatives}, YEAR = {2008}, KEYWORDS = {Language Resources, Technology Infrastucture}, URL = {https://publications.cnr.it/doc/112933}, CONFERENCE_NAME = {LangTech 2008}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {2008}, } @INPROCEEDINGS{REBHOLZSCHUHMANN_2008_INPROCEEDINGS_RPLDKSMMMCA_112935, AUTHOR = {Rebholz Schuhmann, D. and Pezik, P. and Lee, V. and Del Gratta, R. and Kim, J. and Sasaki, Y. and McNaught, J. and Montemagni, S. and Monachini, M. and Calzolari, N. and Ananiadou, S.}, TITLE = {BioLexicon: Towards a reference terminological resource in the biomedical domain}, YEAR = {2008}, ABSTRACT = {The BioLexicon is a publicly available large-scale terminological resource which brings together potential terms from several resources representing selected semantic types (genes, proteins, chemicals, species, enzymes, selected ontological terms). The schema of the BioLexicon enables improved resolution of term ambiguity and follows lexical standards for terminological resources.}, KEYWORDS = {BioLexicon}, URL = {https://publications.cnr.it/doc/112935}, ISBN = {978-1-61567-371-1}, CONFERENCE_NAME = {16th Annual International Conference on Intelligent Systems for Molecular Biology}, CONFERENCE_PLACE = {Toronto, Canada}, CONFERENCE_DATE = {19-23 Luglio 2008}, } @TECHREPORT{MONACHINI_2008_TECHREPORT_MSC_157454, AUTHOR = {Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {The Lexical Grid: Lexical Resources in Language Infrastructures}, YEAR = {2008}, ABSTRACT = {Language Resources are recognized as a central and strategic for the development of any Human Language Technology system and application product. they play a critical role as horizontal technology and have been recognized in many occasions as a priority also by national and spra-national funding a number of initiatives (such as EAGLES, ISLE, ELRA) to establish some sort of coordination of LR activities, and a number of large LR creation projects, both in the written and in the speech areas.}, KEYWORDS = {Human Language Technology, Language Resources}, URL = {https://publications.cnr.it/doc/157454}, } @TECHREPORT{TOKUNAGA_2008_TECHREPORT_TCHKSYCCHKMPS_157453, AUTHOR = {Tokunaga, T. and Calzolari, N. and Huang, C. and Kiyoaki, S. and Sornlertlamvanich, V. and Yingju, X. and Charoenporn, T. and Chung, S. and Hsieh, S. and Kaplan, D. and Monachini, M. and Prévot, L. and Soria, C.}, TITLE = {Developing International Standards of Language Resources for Semantic Web Applications-Research Report of the International Joint Research Program NEDO}, YEAR = {2008}, ABSTRACT = {This report describes a three-year project aiming at an international standard for language resources that includes Asian languages. We summarise our contribution to an international standard of lexical markup framework (LMF) and introduce a prototype query expansion system using LMF-compliant lexical resources. Since ISO 24613 was in the FDIS stage and fairly stable, we built sample lexicons in Chinese, English, Italian, Japanese, and Thai based on ISO24613. At the same time, we implemented a query expansion system utilising rich linguistic resources including lexicons described in the ISO 24613 framework. We confirmed that a system was feasible which worked on the tested languages (including both Western and Eastern languages) when given lexicons are compliant with the framework.}, KEYWORDS = {International standards, Language resources, Semantic web applications}, URL = {https://publications.cnr.it/doc/157453}, } @ARTICLE{BERTAGNA_2007_ARTICLE_BMSCHHMT_30874, AUTHOR = {Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N. and Huang, C. and Hsieh, S. and Marchetti, A. and Tesconi, M.}, TITLE = {Fostering Intercultural Collaboration: a Web Service Architecture for Cross-Fertilization of Distributed Wordnets}, YEAR = {2007}, ABSTRACT = {Enhancing the development of multilingual lexicons is of foremost importance for intercultural collaboration to take place, as multilingual lexicons are the cornerstone of several multilingual applications. However, the development and maintenance of large-scale, robust multilingual dictionaries is a tantalizing task. In this paper we present a tool, based on a web service architecture, enabling semi-automatic generation of bilingual lexicons through linking of distributed monolingual lexical resources. In addition to lexicon development, the architecture also allows enrichment of monolingual source lexicons through exploitation of the semantic information encoded in corresponding entries. In the paper we describe our case study applied to the Italian and Chinese wordnets, and we illustrate how the architecture can be extended to access distributed multilingual WordNets over the Internet, paving the way to exploitation in a cross-lingual framework of the wealth of information built over the last decade.}, PAGES = {146-158}, URL = {https://publications.cnr.it/doc/30874}, VOLUME = {4568}, PUBLISHER = {Springer (Berlin, Germania)}, ISSN = {0302-9743}, JOURNAL = {Lecture notes in computer science}, } @ARTICLE{BERTAGNA_2007_ARTICLE_BTC_64532, AUTHOR = {Bertagna, F. and Toral, A. and Calzolari, N.}, TITLE = {Evalita 2007: The All-Words WSD Task}, YEAR = {2007}, ABSTRACT = {This report describes the Italian all-words sense disambiguation task organized for EVALITA. The objectives of the task and the type of data prepared and distributed to participants are presented. Moreover, evaluation measures and the results obtained by the participating system are introduced.}, PAGES = {50-52}, URL = {https://publications.cnr.it/doc/64532}, VOLUME = {IV(2)}, } @INCOLLECTION{CALZOLARI_2007_INCOLLECTION_C_136434, AUTHOR = {Calzolari, N.}, TITLE = {A Language Resources Infrastructure: from a vision of few to a reality for many?}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/136434}, } @INCOLLECTION{CALZOLARI_2007_INCOLLECTION_C_136454, AUTHOR = {Calzolari, N.}, TITLE = {Corpus-based lexicon building: an overview across projects, problems, approaches}, YEAR = {2007}, PAGES = {112-139}, URL = {https://publications.cnr.it/doc/136454}, PUBLISHER = {routledge (London, GBR)}, ISBN = {0415338964}, BOOKTITLE = {Corpus linguistics: critical concepts in linguistics}, EDITOR = {Teubert, W. and Krishnamurthy, R.}, } @INCOLLECTION{CALZOLARI_2007_INCOLLECTION_C_136457, AUTHOR = {Calzolari, N.}, TITLE = {Towards a new generation of Language Resources in the Semantic Web Vision}, YEAR = {2007}, ABSTRACT = {In this contribution I touch on issues related to: language resources (LR) and semantics, dynamic resources automatically acquired, and how to go for a new generation of LRs compliant with the Semantic Web (SW) vision, pointing at the potentialities and the need for cross-fertilisation between the two communities of Human Language Technology (HLT) and SW/ontologies. Many of these issues are related to Yorick's work on preferences, lexicons, semantic annotation, and recently to his ideas on the relation between HLT and SW Large scale LRs are unanimously recognised as the necessary infrastructure underlying language technology (LT) (Varile and Zampolli (eds.) 1997). Discussing a few major European initiatives for building harmonised LRs, I highlight how computational lexicons and textual corpora should be considered as complementary views on the lexical space, in the perspective of modelling a new type of resource which is both a lexicon and a corpus together. A "complete" computational lexicon should incorporate and represent our "knowledge of the world". I claim that it is theoretically impossible to achieve completeness within any "static" lexicon. Moreover, choices on the syntagmatic axis are pervasive in language. A sound language infrastructure must encompass both "static" lexicons, as the traditional ones, and "dynamic" systems able to enrich the lexicon with information acquired on-line from large corpora, thus capturing the "actually realised" potentialities, the large range of variation, and the flexibility inherent in the language as it is used. These are the challenges for semantic tagging, which is at the core of the SW vision of giving meaning, in a manner understandable by machines, to the content of Web documents Broadening our perspective into the future, the need for more and more "knowledge intensive" large-size LRs for effective content processing requires a change in the paradigm, and the design of a new generation of LRs, based on open content interoperability standards. The SW notion may be helpful in determining the shape of the LRs of the future, consistent with the vision of an open distributed space of sharable knowledge available on the Web for processing The approach to realise the necessary world-wide linguistic infrastructure requires coverage not only of a range of technical aspects, but also - and maybe most critically - of a number of organisational aspects. An essential aspect for ensuring an integrated basis is to enhance the interchange and cooperation among many communities that act now separately, such as LR and LT developers, Terminology, Semantic Web and Ontology experts, content providers, linguists and so on. This is one of the challenges for the next years, for a usable and useful "language" scenario in the global network}, PAGES = {63-105}, URL = {https://publications.cnr.it/doc/136457}, VOLUME = {36}, PUBLISHER = {Springer (Dordrecht, NLD)}, ISBN = {978-1-4020-5832-5}, BOOKTITLE = {Words and Intelligence II: Essays in honour of Yorick Wilks}, EDITOR = {Ahmad, K. and Brewster, C. and Stevenson, M.}, } @INPROCEEDINGS{BERTAGNA_2007_INPROCEEDINGS_BMSCRTM_172595, AUTHOR = {Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N. and Ronzano, N. and Tesconi, M. and Marchetti, A.}, TITLE = {Cooperative Building of Semantic Resources}, YEAR = {2007}, ABSTRACT = {In this paper we present LexFlow, a framework for the automatic and cooperative enrichment, integration and exploitation of semantic resources. Borrowing from techniques used in the domain of document workflows, we model the activity of lexicon management as a particular case of workflow instance, where lexical entries move across agents and become dynamically updated. We also give an important exploitation example of the semantic resources managed or built thanks to LexFlow, describing its integration with SemKey, a system for semantic collaborative tagging.}, KEYWORDS = {semantic resources, cooperative knowledge definition, semantic tagging}, URL = {https://publications.cnr.it/doc/172595}, ISBN = {3-540-74781-8}, CONFERENCE_NAME = {10th Congress of Italian Association for Artificial Intelligence-Cooperative construction of linguistic knowledge bases Workshop}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {10-13 September 2007}, } @INPROCEEDINGS{CALZOLARI_2007_INPROCEEDINGS_C_84683, AUTHOR = {Calzolari, N.}, TITLE = {Towards a New Generation of Language Resources: global trends and international convergences}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/84683}, CONFERENCE_NAME = {International Conference on Natural Language Processing and Knowledge Engineering}, CONFERENCE_PLACE = {Beijing}, CONFERENCE_DATE = {2007}, } @INPROCEEDINGS{CASELLI_2007_INPROCEEDINGS_CPRC_84668, AUTHOR = {Caselli, T. and Prodanof, I. and Ruimy, N. and Calzolari, N.}, TITLE = {Mapping SIMPLE and TimeML: improving event identification and classification using a semantic lexicon}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/84668}, CONFERENCE_NAME = {GL2007: Fourth International Workshop on Generative Approaches to the Lexicon}, CONFERENCE_PLACE = {Parigi}, CONFERENCE_DATE = {2007}, } @INPROCEEDINGS{FRANCOPOULO_2007_INPROCEEDINGS_FBGCMPS_84673, AUTHOR = {Francopoulo, G. and Bel, N. and George, M. and Calzolari, N. and Monachini, M. and Pet, M. and Soria, C.}, TITLE = {Lexical Markup Framework: an ISO Standard for Semantic Information in NLP Lexicons}, YEAR = {2007}, ABSTRACT = {Lexical Markup Framework (LMF) is a model that provides a common standardized framework for Natural Language Processing (NLP) lexicons. The goals of LMF are to provide a common model for the creation and use of such lexical resources to manage the exchange of data between and among these resources, and to enable the merging of a large number of individual resources to form extensive global electronic resources.}, URL = {https://publications.cnr.it/doc/84673}, ISBN = {978-3-8233-6314-9}, CONFERENCE_NAME = {GLDV2007-Lexical-Semantic and Ontological Resources of the GLDV Working Group on Lexicography at the Biennal Spring Conference}, CONFERENCE_PLACE = {Tubingen}, CONFERENCE_DATE = {13-14/04/2007}, } @INPROCEEDINGS{MONACHINI_2007_INPROCEEDINGS_MQRC_84676, AUTHOR = {Monachini, M. and Quochi, V. and Ruimy, N. and Calzolari, N.}, TITLE = {Lexical Relations and Domain Knowledge: The BioLexicon Meets the Qualia Structure}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/84676}, CONFERENCE_NAME = {GL2007: Fourth International Conference on Generative Approaches to the Lexicon}, CONFERENCE_PLACE = {Parigi}, CONFERENCE_DATE = {10-11 Maggio 2007}, EDITOR = {Bouillon, P. and Danlos, L. and Kanzaki, K.}, } @INPROCEEDINGS{QUOCHI_2007_INPROCEEDINGS_QDSMC_84735, AUTHOR = {Quochi, V. and Del Gratta, R. and Sassolini, E. and Monachini, M. and Calzolari, N.}, TITLE = {Toward a Standard Lexical Resource in the Bio Domain}, YEAR = {2007}, ABSTRACT = {The present paper describes a large-scale lexical resource for the biology domain designed both for human and for machine use. This lexicon aims at semantic interoperability and extendability, through the adoption of ISO-LMF standard for lexical representation and through a granular and distributed encoding of relevant information. The first part of this contribution focuses on three aspects of the model that are of particular interest to the biology community: the treatment of term variants, the representation on bio events and the alignment with a domain ontology. The second part of the paper describes the physical implementation of the model: a relational database equipped with a set of automatic uploading procedures. Peculiarity of the BioLexicon is that it combines features of both terminologies and lexicons. A set verbs relevant for the domain is also represented with full details on their syntactic and semantic argument structure.}, KEYWORDS = {Lexical representation model, Lexical Database, Computational Lexicography, Special Domains, Standards}, PAGES = {295-299}, URL = {https://publications.cnr.it/doc/84735}, PUBLISHER = {Fundacja Uniwersytetu im A. Mickiewicza (Poznan, POL)}, ISBN = {978-83-7177-413-3}, CONFERENCE_NAME = {LTC07-3rd Language and Technology Conference: Human Language Technology. Challenges of the Information Society}, CONFERENCE_PLACE = {Poznan, Poland}, CONFERENCE_DATE = {5-7 Ottobre 2007}, } @TECHREPORT{CALZOLARI_2007_TECHREPORT_CMQSGB_157444, AUTHOR = {Calzolari, N. and Monachini, M. and Quochi, V. and Soria, C. and Goggi, S. and Baroni, P.}, TITLE = {FLaReNet: Fostering Language Resources Network. Grant Agreement n° 617001, eContentPlus}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157444}, } @TECHREPORT{DELGRATTA_2007_TECHREPORT_DMQSC_157425, AUTHOR = {Del Gratta, R. and Monachini, M. and Quochi, V. and Sassolini, E. and Calzolari, N.}, TITLE = {Bio-Lexicon DataBase: Architecture, Concepts and Loading Software}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157425}, } @TECHREPORT{FRANCOPOULO_2007_TECHREPORT_FMC_157433, AUTHOR = {Francopoulo, G. and Monachini, M. and Calzolari, N.}, TITLE = {Lexical Markup Framework: an ISO Standard for Semantic Information in NLP Lexicons}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157433}, } @TECHREPORT{FRANCOPOULO_2007_TECHREPORT_FMC_157435, AUTHOR = {Francopoulo, G. and Monachini, M. and Calzolari, N.}, TITLE = {Lexical Standards for ISO ballot}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157435}, } @TECHREPORT{KRAUWER_2007_TECHREPORT_KWC_157443, AUTHOR = {Krauwer, S. and Wittenburg, P. and Calzolari, N.}, TITLE = {CLARIN-Common Language Resources Infrastructure, Grant Agreement n° 212230 7thFP Common Research Infrastrucures}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157443}, } @MISC{TESCONI_2007_MISC_TMBMSC_157409, AUTHOR = {Tesconi, M. and Marchetti, A. and Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {LeXFlow: a Prototype Supporting Collaborative Lexicon Development and Cross-fertilization}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157409}, } @INCOLLECTION{CALZOLARI_2006_INCOLLECTION_C_136451, AUTHOR = {Calzolari, N.}, TITLE = {A Language Resources Infrastructure: from a vision of few to a reality for many?}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/136451}, } @INCOLLECTION{CALZOLARI_2006_INCOLLECTION_C_136452, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources and Content Interoperability: technical, strategic and political issues for a new generation of Language Resources}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/136452}, } @INCOLLECTION{CALZOLARI_2006_INCOLLECTION_C_136453, AUTHOR = {Calzolari, N.}, TITLE = {11. Computational Linguistics}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/136453}, PUBLISHER = {EOLSS Publishers (Oxford, GBR)}, } @INPROCEEDINGS{CALZOLARI_2006_INPROCEEDINGS_CSSCPBEMSC_84625, AUTHOR = {Calzolari, F. and Sassolini, E. and Sassi, M. and Cucurullo, S. and Picchi, E. and Bertagna, F. and Enea, A. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {Next Generation Language Resources using Grid}, YEAR = {2006}, ABSTRACT = {This paper presents a case study concerning the challenges and requirements posed by next generation language resources, realized as an overall model of open, distributed and collaborative language infrastructure. If a sort of "new paradigm" for language resource sharing is required, we think that the emerging and still evolving technology connected to Grid computing is a very interesting and suitable one for a concrete realization of this vision. Given the current limitations of Grid computing, it is very important to test the new environment on basic language analysis tools, in order to get the feeling of what are the potentialities and possible limitations connected to its use in NLP. For this reason, we have done some experiments on a module of the Linguistic Miner, i.e. the extraction of linguistic patterns from restricted domain corpora. The Grid environment has produced the expected results (reduction of the processing time, huge storage capacity, data redundancy) without any additional cost for the final user.}, KEYWORDS = {grid, acquisition, topic classification}, PAGES = {1858-1861}, URL = {https://publications.cnr.it/doc/84625}, ISBN = {2-9517408-2-4}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genova}, CONFERENCE_DATE = {24-26 Maggio 2006}, } @INPROCEEDINGS{CALZOLARI_2006_INPROCEEDINGS_C_84626, AUTHOR = {Calzolari, N.}, TITLE = {Introduction of the Conference Chair}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84626}, CONFERENCE_NAME = {LREC 2006: Book of Abstracts 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genoa}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{CALZOLARI_2006_INPROCEEDINGS_C_84627, AUTHOR = {Calzolari, N.}, TITLE = {Community Culture in Linguistics – an international perspective}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84627}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genoa}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{CALZOLARI_2006_INPROCEEDINGS_C_84647, AUTHOR = {Calzolari, N.}, TITLE = {Technical and Strategic Issues on Language Resources for a Research Infrastructure}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84647}, CONFERENCE_NAME = {International Symposium on Large-scale Knowledge Resources (LKR2006)}, CONFERENCE_PLACE = {Tokyo}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{CALZOLARI_2006_INPROCEEDINGS_C_84648, AUTHOR = {Calzolari, N.}, TITLE = {International Standards for Computational Lexicons: their relation to terminology}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84648}, CONFERENCE_NAME = {TSTT 2006, International Conference on terminology, Standardization and Technology Transfer}, CONFERENCE_PLACE = {Beijing}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{FRANCOPOULO_2006_INPROCEEDINGS_FBGCMPS_84649, AUTHOR = {Francopoulo, G. and Bel, N. and George, M. and Calzolari, N. and Monachini, M. and Pet, M. and Soria, C.}, TITLE = {Lexical markup framework (LMF) for NLP multilingual resources}, YEAR = {2006}, ABSTRACT = {Optimizing the production, maintenance and extension of lexical resources is one of the crucial aspects impacting Natural Language Processing (NLP). A second aspect involves optimizing the process leading to their integration into applications. In this respect, we believe that the production of a consensual specification on multilingual lexicons can be a useful aid for the various NLP actors. Within ISO, one purpose of LMF (ISO-24613) is to define a standard for lexicons that covers multilingual data.}, PAGES = {1-8}, URL = {https://publications.cnr.it/doc/84649}, ISBN = {1-932432-69-8}, CONFERENCE_NAME = {COLING-ACL Workshop on Multilingual Lexical Resources and Interoperability}, CONFERENCE_PLACE = {Sydney (Australia)}, CONFERENCE_DATE = {2006}, BOOKTITLE = {Proceedings of the Workshop on Multilingual Language Resources and Interoperability}, } @INPROCEEDINGS{FRANCOPOULO_2006_INPROCEEDINGS_FGCMBPS_84632, AUTHOR = {Francopoulo, G. and George, M. and Calzolari, N. and Monachini, M. and Bel, N. and Pet, M. and Soria, C.}, TITLE = {LMF for multilingual, specialized lexicons}, YEAR = {2006}, PAGES = {27-32}, URL = {https://publications.cnr.it/doc/84632}, ISBN = {2-9517408-2-4}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genova}, CONFERENCE_DATE = {24-26 Maggio 2006}, } @INPROCEEDINGS{FRANCOPOULO_2006_INPROCEEDINGS_FGCMBPS_84633, AUTHOR = {Francopoulo, G. and George, M. and Calzolari, N. and Monachini, M. and Bel, N. and Pet, M. and Soria, C.}, TITLE = {Lexical Markup Framework (LMF)}, YEAR = {2006}, ABSTRACT = {Optimizing the production, maintenance and extension of lexical resources is one the crucial aspects impacting Natural Language Processing (NLP). A second aspect involves optimizing the process leading to their integration in applications. With this respect, we believe that the production of a consensual specification on lexicons can be a useful aid for the various NLP actors. Within ISO, the purpose of LMF is to define a standard for lexicons. LMF is a model that provides a common standardized framework for the construction of NLP lexicons. The goals of LMF are to provide a common model for the creation and use of lexical resources, to manage the exchange of data between and among these resources, and to enable the merging of large number of individual electronic resources to form extensive global electronic resources. In this paper, we describe the work in progress within the sub-group ISO-TC37/SC4/WG4. Various experts from a lot of countries have been consulted in order to take into account best practices in a lot of languages for (we hope) all kinds of NLP lexicons.}, PAGES = {233-236}, URL = {https://publications.cnr.it/doc/84633}, PUBLISHER = {European Language Resources Association (ELRA)-Evaluations and Language resources Distribution Agency (ELDA) (Paris, FRA)}, ISBN = {2-9517408-2-4}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genoa}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{GIOULI_2006_INPROCEEDINGS_GLGPMSCC_84634, AUTHOR = {Giouli, V. and Labropoulou, P. and Gavrilidou, M. and Piperidis, S. and Monachini, M. and Soria, C. and Calzolari, N. and Choukri, K.}, TITLE = {Language Resources Production Models: the Case of the INTERA Multilingual Corpus and Terminology}, YEAR = {2006}, ABSTRACT = {This paper reports on the multilingual Language Resources (MLRs), i.e. parallel corpora and terminological lexicons for less widely digitally available languages, that have been developed in the INTERA project and the methodology adopted for their production. Special emphasis is given to the reality factors that have influenced the MLRs development approach and their final constitution. Building on the experience gained in the project, a production model has been elaborated, suggesting ways and techniques that can be exploited in order to improve LRs production taking into account realistic issues.}, KEYWORDS = {multilingual parallel corpora, language resources production models, less widely digitally available languages}, PAGES = {609-614}, URL = {https://publications.cnr.it/doc/84634}, ISBN = {2-9517408-2-4}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genova}, CONFERENCE_DATE = {24-26 Maggio 2006}, } @INPROCEEDINGS{MARCHETTI_2006_INPROCEEDINGS_MTRRBMSCHH_84652, AUTHOR = {Marchetti, A. and Tesconi, M. and Ronzano, F. and Rosella, M. and Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N. and Huang, C. R. and Hsieh, S. K.}, TITLE = {Towards an Architecture for the GlobalWordNet Initiative}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84652}, CONFERENCE_NAME = {SWAP-06, the 3rd Italian Semantic Web Workshop}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{MARCHETTI_2006_INPROCEEDINGS_MTRRBMSCHH_263653, AUTHOR = {Marchetti, A. and Tesconi, M. and Ronzano, F. and Rosella, M. and Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N. and Huang, C. and Hsieh, S.}, TITLE = {Toward an Architecture for the Global Wordnet Initiative}, YEAR = {2006}, ABSTRACT = {Enhancing the development of multilingual lexicons is of foremost importance for intercultural collaboration to take place, as multilingual lexicons are the cornerstone of several multilingual applications. However, the development and maintenance of large-scale, robust multilingual dictionaries is a tantalizing task. Moreover, Semantic Web's growing interest towards the availability of high-quality lexical resources and their multilingual interoperability, is focusing more and more attention on this topic. In this paper we present a tool, based on a web service architecture, enabling semi-automatic generation of bilingual lexicons through linking of distributed monolingual lexical resources. In addition to lexicon development, the architecture also allows enrichment of monolingual source lexicons through exploitation of the semantic information encoded in corresponding entries. In the paper we describe our case study applied to the Italian and Chinese wordnets, and we illustrate how the architecture can be extended to access distributed multilingual WordNets over the Internet, paving the way to exploitation in a cross-lingual framework of the wealth of information built over the last decade.}, KEYWORDS = {Lexical resource, wordnet, multilingual interoperability, semantic web}, PAGES = {7-35}, URL = {http://ceur-ws.org/Vol-201/35.pdf}, CONFERENCE_NAME = {SWAP 2006-Semantic Web Applications and Perspectives}, CONFERENCE_PLACE = {Pisa, Italy}, CONFERENCE_DATE = {18-20 December, 2006}, } @INPROCEEDINGS{MONACHINI_2006_INPROCEEDINGS_MCCFMMOU_84639, AUTHOR = {Monachini, M. and Calzolari, N. and Choukri, K. and Friedrich, J. and Maltese, G. and Mammini, M. and Odijk, J. and Ulivieri, M.}, TITLE = {Unified Lexicon and Unified Morphosyntactic Specifications for Written and Spoken Italian}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84639}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genoa}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{SORIA_2006_INPROCEEDINGS_STBCMM_171465, AUTHOR = {Soria, C. and Tesconi, M. and Bertagna, F. and Calzolari, N. and Marchetti, A. and Monachini, M.}, TITLE = {Moving to dynamic computational lexicons with LeXFlow}, YEAR = {2006}, ABSTRACT = {LeXFlow is a framework for semi-automatic integration of lexicons, already expressed in standardized format. LeXFlow is intended as a tool for, on the one hand, paving the way to the development of dynamic multi-source lexicons; and on the other, for fostering the adoption of standards. Borrowing from techniques used in the domain of document workflows, we model the activity of lexicon management as a particular case of workflow instance, where lexical entries move across agents and become dynamically updated. To this end, we have designed a lexical flow (LF) corresponding to the scenario where an entry of a lexicon A becomes enriched via basically two steps. First, by virtue of being mapped onto a corresponding entry belonging to a lexicon B, the entry(LA) inherits the semantic relations available in B. Second, by resorting to an automatic application that acquires information about semantic relations from corpora, the relations acquired are integrated into the entry and proposed to the human encoder. As a result of the lexical flow, in addition, for each starting lexical entry(LA) mapped onto a corresponding entry(LB) the flow produces a new entry representing the merging of the original two entries.}, KEYWORDS = {computational lexicons, collaborative authoring}, PAGES = {12}, URL = {https://publications.cnr.it/doc/171465}, ISBN = {2-9517408-2-4}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Genova}, CONFERENCE_DATE = {24-26 Maggio 2006}, } @INPROCEEDINGS{TESCONI_2006_INPROCEEDINGS_TMBMHCS_173931, AUTHOR = {Tesconi, M. and Marchetti, A. and Bertagna, F. and Monachini, M. and Huang, C. and Calzolari, N. and Soria, C.}, TITLE = {Towards agent-based cross-lingual interoperability of distributed lexical resources}, YEAR = {2006}, ABSTRACT = {In this paper we present an application fostering the integration and interoperability of computational lexicons, focusing on the particular case of mutual linking and cross-lingual enrichment of two wordnets, ItalWordNet and Sinica-BOW lexicons. This is intended as a case-study investingating the needs and requirements of semi-automatic integration and interoperability of lexical resources.}, KEYWORDS = {wordnet, multilingual computational lexicons, collaborative authoring}, PAGES = {17-24}, URL = {https://publications.cnr.it/doc/173931}, ISBN = {1-932432-69-8}, CONFERENCE_NAME = {ACL Workshop on Multilingual Lexical Resources and Interoperability}, CONFERENCE_PLACE = {Sydney (Australia)}, CONFERENCE_DATE = {15-23 Luglio 2006}, BOOKTITLE = {Proceedings of the Workshop on Multilingual Language Resources and Interoperability}, } @INPROCEEDINGS{TESCONI_2006_INPROCEEDINGS_TMBMSC_83590, AUTHOR = {Tesconi, M. and Marchetti, A. and Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {LeXFlow: a system for cross-fertilization of computational lexicons}, YEAR = {2006}, ABSTRACT = {This demo presents LeXFlow, a workflow management system for crossfertilization of computational lexicons. Borrowing from techniques used in the domain of document workflows, we model the activity of lexicon management as a set of workflow types, where lexical entries move across agents in the process of being dynamically updated. A prototype of LeXFlow has been implemented with extensive use of XML technologies (XSLT, XPath, XForms, SVG) and open-source tools (Cocoon, Tomcat, MySQL). LeXFlow is a web-based application that enables the cooperative and distributed management of computational lexicons.}, KEYWORDS = {computational lexicons, collaborative authoring}, URL = {https://publications.cnr.it/doc/83590}, DOI = {10.3115/1225403.1225406}, CONFERENCE_NAME = {COLING-ACL '06 Proceedings of the COLING/ACL on Interactive presentation sessions}, CONFERENCE_PLACE = {Sydney (Australia)}, CONFERENCE_DATE = {16-23 luglio 2006}, } @INPROCEEDINGS{TESCONI_2006_INPROCEEDINGS_TMBMSC_84656, AUTHOR = {Tesconi, M. and Marchetti, A. and Bertagna, F. and Monachini, M. and Soria, C. and Calzolari, N.}, TITLE = {LeXFlow: a framework for cross-fertilization of computational lexicons}, YEAR = {2006}, ABSTRACT = {This demo presents LeXFlow, a workflow management system for cross-fertilization of computational lexicons. Borrowing from techniques used in the domain of document workflows, we model the activity of lexicon management as a set of workflow types, where lexical entries move across agents in the process of being dynamically updated. A prototype of LeXFlow has been implemented with extensive use of XML technologies (XSLT, XPath, XForms, SVG)and open-source tools (Cocoon, Tomcat, MySQL). LeXFlow is a web-based application that enables the cooperative and distributed management of computational lexicons.}, PAGES = {9-12}, URL = {https://publications.cnr.it/doc/84656}, ISBN = {1-932432-69-8}, CONFERENCE_NAME = {COLING/ACL 2006}, CONFERENCE_PLACE = {Sydney (Australia)}, CONFERENCE_DATE = {15-23 Luglio 2006}, BOOKTITLE = {Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions}, } @INPROCEEDINGS{TOKUNAGA_2006_INPROCEEDINGS_TSCCMSHPXYK_84657, AUTHOR = {Tokunaga, T. and Sornlertlamvanich, V. and Charoenporn, T. and Calzolari, N. and Monachini, M. and Soria, C. and Huang, C. and Prevot, L. and Xia, Y. and Yu, H. and Kiyoaki, S.}, TITLE = {Infrastructure for standardization of Asian language resources}, YEAR = {2006}, ABSTRACT = {As an area of great linguistic and cultural diversity, Asian language resources have received much less attention than their western counterparts. Creating a common standard for Asian language resources that is compatible with an international standard has at least three strong advantages: to increase the competitive edge of Asian countries, to bring Asian countries to closer to their western counterparts, and to bring more cohesion among Asian countries. To achieve this goal, we have launched a two year project to create a common standard for Asian language resources. The project is comprised of four research items, (1) building a description framework of lexical entries, (2) building sample lexicons, (3) building an upper-layer ontology and (4) evaluating the proposed framework through an application. This paper outlines the project in terms of its aim and approach.}, PAGES = {827-834}, URL = {https://publications.cnr.it/doc/84657}, ISBN = {1-932432-69-8}, CONFERENCE_NAME = {COLING/ACL 2006}, CONFERENCE_PLACE = {Sydney (Australia)}, CONFERENCE_DATE = {15-26 luglio 2006}, BOOKTITLE = {Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions}, } @TECHREPORT{CALZOLARI_2006_TECHREPORT_C_157397, AUTHOR = {Calzolari, N.}, TITLE = {Language Technologies (LT)}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/157397}, } @TECHREPORT{MONACHINI_2006_TECHREPORT_MSCFB_157402, AUTHOR = {Monachini, M. and Soria, C. and Calzolari, N. and Francopoulo, G. and Bel, N.}, TITLE = {WD of Lexica standard for CD ballot}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/157402}, } @TECHREPORT{QUOCHI_2006_TECHREPORT_QMCDS_157403, AUTHOR = {Quochi, V. and Monachini, M. and Calzolari, N. and Del Gratta, R. and Sassolini, E.}, TITLE = {Bio-Lexicon Model and Preliminary ISO Conformant Data Categories}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/157403}, } @TECHREPORT{RUIMY_2006_TECHREPORT_RMC_157404, AUTHOR = {Ruimy, N. and Monachini, M. and Calzolari, N.}, TITLE = {Lessico Computazionale Multilivello dell'Italiano PAROLE-SIMPLE-CLIPS}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/157404}, } @MISC{ROVENTINI_2006_MISC_RABCM_151559, AUTHOR = {Roventini, A. and Alonge, A. and Bertagna, F. and Calzolari, N. and Marinelli, R.}, TITLE = {ItalWordNet database semantico-lessicale dell’italiano}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/151559}, } @ARTICLE{CALZOLARI_2005_ARTICLE_C_64513, AUTHOR = {Calzolari, N.}, TITLE = {Foreword}, YEAR = {2005}, PAGES = {9-17}, URL = {https://publications.cnr.it/doc/64513}, VOLUME = {22-23}, } @ARTICLE{CALZOLARI_2005_ARTICLE_C_64514, AUTHOR = {Calzolari, N.}, TITLE = {Antonio Zampolli and computational linguistics}, YEAR = {2005}, PAGES = {497-517}, URL = {https://publications.cnr.it/doc/64514}, VOLUME = {15 /4}, } @ARTICLE{CALZOLARI_2005_ARTICLE_CI_168525, AUTHOR = {Calzolari, N. and Ide, N.}, TITLE = {Language Resources and Evaluation}, YEAR = {2005}, PAGES = {1-118}, URL = {https://publications.cnr.it/doc/168525}, VOLUME = {39}, PUBLISHER = {Kluwer Academic Publishers (Dordrecht, Paesi Bassi)}, ISSN = {0010-4817}, JOURNAL = {Computers and the humanities (Print)}, } @ARTICLE{IDE_2005_ARTICLE_IC_30868, AUTHOR = {Ide, N. and Calzolari, N.}, TITLE = {Introduction to the Special Inaugural Issue}, YEAR = {2005}, ABSTRACT = {This first issue of Language Resources and Evaluation is dedicated to the memory of Antonio Zampolli, whom few would dispute is the one person who has led the way in promoting and establishing the development of language resources (LR) of all kinds for the past four decades. In this inaugural issue, we have attempted to bring together articles by major figures in the field in order to provide an overview of the history, state of the art, and the future of the creation, annotation, exploitation, evaluation, and distribution of LR. Hopefully, this collection of articles will serve not only as a tribute to Antonio, but also as a framework out of which this journal – which almost certainly would not have existed were it not for him – can grow.}, KEYWORDS = {Antonio Zampolli, language resources and evaluation}, PAGES = {1-7}, URL = {https://publications.cnr.it/doc/30868}, VOLUME = {39}, PUBLISHER = {Kluwer Academic Publishers (Dordrecht, Paesi Bassi)}, ISSN = {0010-4817}, JOURNAL = {Computers and the humanities (Print)}, } @ARTICLE{MAEGAARD_2005_ARTICLE_MCCO_30872, AUTHOR = {Maegaard, B. and Choukri, K. and Calzolari, N. and Odijk, J.}, TITLE = {ELRA – European Language Resources Association-Background, Recent Developments and Future Perspectives}, YEAR = {2005}, ABSTRACT = {The European Language Resources Association (ELRA) was founded in 1995 with the mission of providing language resources (LR) to European research institutions and companies. In this paper we describe the background, the mission and the major activities since then.}, KEYWORDS = {evaluation, language resources, production, standards, validation}, PAGES = {9-23}, URL = {https://publications.cnr.it/doc/30872}, VOLUME = {39}, DOI = {10.1007/s10579-005-2692-5}, PUBLISHER = {Springer (Dordrecht, Paesi Bassi)}, ISSN = {1574-020X}, JOURNAL = {Language resources and evaluation (Print)}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_84577, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources and Content Interoperability. Technical, strategic and political issues for a new generation of Language Resources}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/84577}, CONFERENCE_NAME = {IX Simposio Internacional de Comunicación Social}, CONFERENCE_PLACE = {Santiago de Cuba}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_84578, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources: priorities and challenges}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/84578}, CONFERENCE_NAME = {Symposium on Natural Processing and Image Recognition}, CONFERENCE_PLACE = {Kyoto}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_84594, AUTHOR = {Calzolari, N.}, TITLE = {Antonio Zampolli-A life Computational Linguistics}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/84594}, CONFERENCE_NAME = {L\&T'05-2nd Language Technologies as a Challenge for Computer Science and Linguistics}, CONFERENCE_PLACE = {Poznan, Poland}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_84646, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources, Language Technology, Linguistics: isn’t this too narrow?}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/84646}, CONFERENCE_NAME = {Human Language Technologies as a Challenge for Computer Science and Linguistics, 2nd L\&T'05}, CONFERENCE_PLACE = {Poznan (Poland)}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_CS_84595, AUTHOR = {Calzolari, N. and Soria, C.}, TITLE = {A new paradigm for an Open Distributed Language Resource Infrastructure: the case of Computational Lexicons}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/84595}, CONFERENCE_NAME = {Knowledge Collection from Volunteer Contributors. Papers from the 2005 AAAI Spring Symposium}, CONFERENCE_PLACE = {Stanford}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{MONACHINI_2005_INPROCEEDINGS_MC_84585, AUTHOR = {Monachini, M. and Calzolari, N.}, TITLE = {Initiatives towards the integration of Lexicons: MILE is taking steps forward}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/84585}, CONFERENCE_NAME = {Machine Translation}, CONFERENCE_PLACE = {Kothen, Germany}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112901, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources and Content Interoperability – Technical, strategic and political issues for a new generation of Language Resources}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112901}, CONFERENCE_NAME = {9th International Symposium on Social Communication}, CONFERENCE_PLACE = {Santiago de Cuba}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112902, AUTHOR = {Calzolari, N.}, TITLE = {Building Blocks for Semantic Annotation: towards Content Interoperability}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112902}, CONFERENCE_NAME = {6oth anniversary of Bente Maegaard}, CONFERENCE_PLACE = {Copenhagen}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112903, AUTHOR = {Calzolari, N.}, TITLE = {Antonio Zampolli-A life for Computational Linguistics}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112903}, CONFERENCE_NAME = {Human Language Technologies as a Challenge for Computer Science and Linguistics}, CONFERENCE_PLACE = {Poznañ}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112904, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources, Language Technology, Linguistics: isn’t this too narrow?}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112904}, CONFERENCE_NAME = {Human Language Technologies as a Challenge for Computer Science and Linguistics}, CONFERENCE_PLACE = {Poznañ}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112905, AUTHOR = {Calzolari, N.}, TITLE = {Building blocks for semantic markup: towards a framework for content interoperability}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112905}, CONFERENCE_NAME = {GL ‘2005 Third International Workshop on Generative Approaches to the Lexicon}, CONFERENCE_PLACE = {Genève}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112906, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources: Standardisation, re-use, automated LR acquisition}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112906}, CONFERENCE_NAME = {Science \& Technology Forum on Multilingualism}, CONFERENCE_PLACE = {Luxembourg}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112907, AUTHOR = {Calzolari, N.}, TITLE = {Language Technology and the Semantic Web}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112907}, CONFERENCE_NAME = {ECOR – European Centre for Ontological Research Inaugural Meeting}, CONFERENCE_PLACE = {Saarbrücken}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112908, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources: towards a framework for content interoperability}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112908}, CONFERENCE_NAME = {AIIA Workshop on Current challenges in speech and natural language processing}, CONFERENCE_PLACE = {Milano}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112909, AUTHOR = {Calzolari, N.}, TITLE = {Language resources: priorities and challenges}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112909}, CONFERENCE_NAME = {International Symposium on Natural Language Processing and Image Recognition}, CONFERENCE_PLACE = {Kyoto}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112910, AUTHOR = {Calzolari, N.}, TITLE = {Linguistica computazionale: sinergie con il progetto DLM}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112910}, CONFERENCE_NAME = {Convegno Lessicologia e Metalinguaggio}, CONFERENCE_PLACE = {Macerata}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112911, AUTHOR = {Calzolari, N.}, TITLE = {Linguistica Computazionale: che cosa ci dice della lingua?}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112911}, CONFERENCE_NAME = {Convegno Istanze epistemologiche e ontologiche emergenti dalle scienze informatiche}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112912, AUTHOR = {Calzolari, N.}, TITLE = {An Infrastructure for Language Technology and more}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112912}, CONFERENCE_NAME = {Language Documentation and Language Description}, CONFERENCE_PLACE = {Bielefeld}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_C_112913, AUTHOR = {Calzolari, N.}, TITLE = {Technical and Strategic Issues on Language Resources for a Research Infrastructure}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/112913}, CONFERENCE_NAME = {Large-scale Knowledge Resources (LKR2006)}, CONFERENCE_PLACE = {Tokyo}, CONFERENCE_DATE = {2005}, } @INPROCEEDINGS{CALZOLARI_2005_INPROCEEDINGS_CBLM_157387, AUTHOR = {Calzolari, N. and Bertagna, F. and Lenci, A. and Monachini, M.}, TITLE = {Boosting Lexical Resources for the Semantic Web. Generative Lexicon and Lexicon Interoperability}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/157387}, CONFERENCE_NAME = {GL2005-3rd International Workshop on Generative Approaches to the Lexicon}, CONFERENCE_PLACE = {Genève, Switzerland}, CONFERENCE_DATE = {19-21 Maggio 2005}, } @TECHREPORT{FRANCOPOULO_2005_TECHREPORT_FGCMBPS_157379, AUTHOR = {Francopoulo, G. and George, M. and Calzolari, N. and Monachini, M. and Bel, N. and Pet, M. and Soria, C.}, TITLE = {Language Resource Management – Lexical Markup Framework}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/157379}, } @TECHREPORT{MONACHINI_2005_TECHREPORT_MSUCDM_157386, AUTHOR = {Monachini, M. and Soria, C. and Ulivieri, M. and Calzolari, N. and Declerck, T. and Mammini, M.}, TITLE = {Evaluation of existing standards for NLP Lexica: Proposal for Candidate Data Categories}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/157386}, } @MISC{FRANCOPOULO_2005_MISC_FGCMBPS_151541, AUTHOR = {Francopoulo, G. and George, M. and Calzolari, N. and Monachini, M. and Bel, N. and Pet, M. and Soria, C.}, TITLE = {Lexical Markup Framework}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/151541}, } @MISC{MONACHINI_2005_MISC_MSUCDM_151542, AUTHOR = {Monachini, M. and Soria, C. and Ulivieri, M. and Calzolari, N. and Declerck, T. and Mammini, M.}, TITLE = {Data Category Registry}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/151542}, } @MISC{ROVENTINI_2005_MISC_RABCM_151536, AUTHOR = {Roventini, A. and Alonge, A. and Bertagna, F. and Calzolari, N. and Marinelli, R.}, TITLE = {ItalWordNet database semantico-lessicale dell’italiano}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/151536}, } @MISC{RUIMY_2005_MISC_RMC_151535, AUTHOR = {Ruimy, N. and Monachini, M. and Calzolari, N.}, TITLE = {Lessico elettronico multi-livello dell'italiano: PAROLE-SIMPLE-CLIPS}, YEAR = {2005}, URL = {https://publications.cnr.it/doc/151535}, } @ARTICLE{CALZOLARI_2004_ARTICLE_C_64511, AUTHOR = {Calzolari, N.}, TITLE = {The Strategic Role of LRs: ENABLER and the Committee for Written LRs and Evaluation}, YEAR = {2004}, PAGES = {3-4}, URL = {https://publications.cnr.it/doc/64511}, VOLUME = {13. 1}, } @ARTICLE{CALZOLARI_2004_ARTICLE_CL_64512, AUTHOR = {Calzolari, N. and Lenci, A.}, TITLE = {Linguistica Computazionale-Strumenti e risorse per il Trattamento Automatico della Lingua}, YEAR = {2004}, PAGES = {56-69}, URL = {https://publications.cnr.it/doc/64512}, VOLUME = {2}, } @ARTICLE{MAGNINI_2004_ARTICLE_MC_64503, AUTHOR = {Magnini, B. and Calzolari, N.}, TITLE = {Temi e prospettive di ricerca per l’elaborazione del linguaggio naturale in Italia-Topics and Research Perspectives for Natural Language Processing in Italy}, YEAR = {2004}, PAGES = {50-51}, URL = {https://publications.cnr.it/doc/64503}, VOLUME = {I (1)}, } @INCOLLECTION{CALZOLARI_2004_INCOLLECTION_C_136442, AUTHOR = {Calzolari, N.}, TITLE = {Computational Lexicons and Corpora: Complementary Components in Human Language Technology}, YEAR = {2004}, ABSTRACT = {Language resources (LR) are unanimously recognised as a necessary preliminary platform for developing an adequate human language technology (HLT). In this paper I touch on a few issues related to computational lexicon and textual corpora, highlighting how evidence shows that they are not only two closely interrelated linguistic objects, but should be considered as complementary view on the lexical space.}, PAGES = {89-107}, URL = {https://publications.cnr.it/doc/136442}, PUBLISHER = {John Benjamins (Amsterdam, NLD)}, ISBN = {1588115372}, BOOKTITLE = {Linguistic Today-Facing a Greater Challenge}, EDITOR = {Van Sterkenburg, P.}, } @INCOLLECTION{CALZOLARI_2004_INCOLLECTION_CP_136440, AUTHOR = {Calzolari, N. and Paoloni, A.}, TITLE = {Il Trattamento Automatico della Lingua: definizione e aree tecnologiche}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/136440}, PUBLISHER = {Fondazione Ugo Bordoni (Roma, ITA)}, } @INCOLLECTION{CALZOLARI_2004_INCOLLECTION_CP_136441, AUTHOR = {Calzolari, N. and Paoloni, A.}, TITLE = {TAL: Definitions and Technical Areas}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/136441}, PUBLISHER = {Fondazione Ugo Bordoni (Roma, ITA)}, } @INPROCEEDINGS{BERTAGNA_2004_INPROCEEDINGS_BCMSU_84572, AUTHOR = {Bertagna, F. and Calzolari, N. and Monachini, M. and Soria, C. and Ulivieri, M.}, TITLE = {Report on the interlingual annotation experience at ILC-CNR}, YEAR = {2004}, URL = {http://www.google.com/url?sa=t\&rct=j\&q=\&esrc=s\&source=web\&cd=1\&ved=0CDQQFjAA\&url=http%3A%2F%2Fciteseerx.ist.psu.edu%2Fviewdoc%2Fdownload%3Fdoi%3D10.1.1.92.5078%26rep%3Drep1%26type%3Dpdf\&ei=ksa5UZOcJ8mjhgeziIGQBw\&usg=AFQjCNE1nXfd9hHiIstx1Lq_4VaiGDvkkA\&sig2=fIUJ3FE3BnBgDALu5T832w\&bvm=bv.47883778,d.ZG4}, CONFERENCE_NAME = {Seventh Interlingua Workshop on Determining Interlingua Utility for Machine Translation}, CONFERENCE_PLACE = {Washington DC}, CONFERENCE_DATE = {2 Ottobre 2004}, BOOKTITLE = {Biennal Conference of the AMTA-Determining Interlingua Utility for Machine Translation}, EDITOR = {Habash, N. and Dorr, B. and Hovy, E. and Reeder, F.}, } @INPROCEEDINGS{BERTAGNA_2004_INPROCEEDINGS_BLMC_84573, AUTHOR = {Bertagna, F. and Lenci, A. and Monachini, M. and Calzolari, N.}, TITLE = {The MILE Lexical Classes: Data Categories for Content Interoperability among Lexicons}, YEAR = {2004}, PAGES = {8}, URL = {https://publications.cnr.it/doc/84573}, ISBN = {2-9517408-1-6}, CONFERENCE_NAME = {LREC 2004: Fourth International Conference on Language Resources and Evaluation-Workshop: A Registry of Linguistic Data Categories within an Integrated Language Resources Repository Area (INTERA)}, CONFERENCE_PLACE = {Lisbon, Portugal}, CONFERENCE_DATE = {29-5-2004}, } @INPROCEEDINGS{BERTAGNA_2004_INPROCEEDINGS_BLMC_84574, AUTHOR = {Bertagna, F. and Lenci, A. and Monachini, M. and Calzolari, N.}, TITLE = {Content Interoperability of Lexical Resources: Open Issues and MILE Perspectives}, YEAR = {2004}, ABSTRACT = {The paper tackles the issue of content interoperability among lexical resources, by presenting an experiment of mapping differently conceived lexicons, FrameNet and NOMLEX, onto MILE (Multilingual ISLE Lexical Entry), a meta-entry for the encoding of multilingual lexical information, acting as a general schema of shared and common lexical objects. The aim is to (i) raise problems and (ii) test the expressive potentialities of MILE as a standard environment for Computational Lexicons.}, PAGES = {131-134}, URL = {https://publications.cnr.it/doc/84574}, ISBN = {2-9517408-1-6}, CONFERENCE_NAME = {LREC 2004: Fourth International Conference on Language Resources and Evaluation, held in Memory of Antonio Zampolli. Lisbon, Portugal, Proceedings, Volume I, Paris, The European Language Resources Association (ELRA)}, CONFERENCE_PLACE = {Lisbon, Portugal}, CONFERENCE_DATE = {26-27-28 May 2004}, } @INPROCEEDINGS{BUSEMANN_2004_INPROCEEDINGS_BCCK_84569, AUTHOR = {Busemann, S. and Calzolari, N. and Choukri, K. and Krauwer, S.}, TITLE = {Building the LR&E Roadmap: Joint COCOSDA and ICCWLRE Meeting}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84569}, CONFERENCE_NAME = {LREC 2004}, CONFERENCE_PLACE = {Lisbona}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_84588, AUTHOR = {Calzolari, N.}, TITLE = {Introduction of the Conference Chair}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84588}, CONFERENCE_NAME = {LREC 2004: Fourth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Lisbona}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_84589, AUTHOR = {Calzolari, N.}, TITLE = {Computational Lexicons-Open and Distributed Lexical Infrastructure}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84589}, CONFERENCE_NAME = {LREC 2004: Fourth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Lisbona}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_84590, AUTHOR = {Calzolari, N.}, TITLE = {Computational Lexicons-Dynamic Lexicons: New types of reseources which are Corpus and Lexicon together}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84590}, CONFERENCE_NAME = {LREC 2004: Fourth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Lisbona}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_84604, AUTHOR = {Calzolari, N.}, TITLE = {European Initiatives to Promote Cooperation between Speech and Text Communities}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84604}, CONFERENCE_NAME = {ICSLP, Interspeech 2004, 8th International Conference on Spoken Language Processing}, CONFERENCE_PLACE = {Korea}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_172460, AUTHOR = {Calzolari, N.}, TITLE = {A new vision for Language Resources: the role of International Cooperation}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/172460}, CONFERENCE_NAME = {Multilingual Information Service System for the Beijing 2008 Olympics Forum}, CONFERENCE_PLACE = {Beijing, China}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_CCGMBFLMMP_84592, AUTHOR = {Calzolari, N. and Choukri, K. and Gavrilidou, M. and Maegaard, B. and Baroni, P. and Fersøe, H. and Lenci, A. and Mapelli, V. and Monachini, M. and Piperidis, S.}, TITLE = {ENABLER Thematic Network of National Projects: Technical, Strategic and Political Issues of LRs}, YEAR = {2004}, ABSTRACT = {In this paper we present general strategies concerning Language Resources (LRs) - Written, Spoken and, recently, Multimodal - as developed within the ENABLER Thematic Network. LRs are a central component of the so-called "linguistic infrastructure" (the other key element being Evaluation), necessary for the development of any Human Language Technology (HLT) application. They play a critical role, as horizontal technology, in different emerging areas of FP6, and have been recognized as a priority within a number of national projects around Europe and world-wide. The availability of LRs is also a "sensitive" issue, touching directly the sphere of linguistic and cultural identity, but also with economical, societal and political implications. This is going to be even more true in the new Europe with 25 languages on a par.}, KEYWORDS = {Language Resources, Strategic and Political Issues, Written and Spoken, Linguistic Infrastructure, Supranational Coordination}, PAGES = {937-940}, URL = {http://www.lrec-conf.org/proceedings/lrec2004/}, VOLUME = {III}, PUBLISHER = {European Language Resources Association (ELRA)-Evaluations and Language resources Distribution Agency (ELDA) (Paris, FRA)}, ISBN = {2-9517408-1-6}, CONFERENCE_NAME = {LREC 2004-Fourth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Lisbon}, CONFERENCE_DATE = {24-30/05/2004}, BOOKTITLE = {Proceedings of the Fourth International Conference on Language Resources and Evaluation}, EDITOR = {Lino, M. T. and Xavier, M. F. and Ferreira, F. and Costa, R. and Silva, R.}, } @INPROCEEDINGS{DECLERCK_2004_INPROCEEDINGS_DBCL_84606, AUTHOR = {Declerck, T. and Buitelaar, P. and Calzolari, N. and Lenci, A.}, TITLE = {Towards a Language Infrastructure for the Semantic Web}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84606}, CONFERENCE_NAME = {2004: Fourth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Lisbona}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{ULIVIERI_2004_INPROCEEDINGS_UGBC_84619, AUTHOR = {Ulivieri, M. and Guazzini, E. and Bertagna, F. and Calzolari, N.}, TITLE = {Senseval-3: The Italian All-words Task}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84619}, CONFERENCE_NAME = {SENSEVAL-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text}, CONFERENCE_PLACE = {Barcellona}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_112898, AUTHOR = {Calzolari, N.}, TITLE = {Le risorse linguistiche: corpora, dizionari, ontologie, …}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/112898}, CONFERENCE_NAME = {Trattamento del Linguaggio Naturale: prospettive della ricerca e del mercato in Italia}, CONFERENCE_PLACE = {Perugia}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_112899, AUTHOR = {Calzolari, N.}, TITLE = {Il Trattamento Automatico della Lingua}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/112899}, CONFERENCE_NAME = {Conferenza stampa per la presentazione del Libro Bianco del Forum TAL}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {2004}, } @INPROCEEDINGS{CALZOLARI_2004_INPROCEEDINGS_C_112900, AUTHOR = {Calzolari, N.}, TITLE = {Semantic tagging and semantic lexicons: towards content interoperability}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/112900}, CONFERENCE_NAME = {International Colloquium on Word structure and Lexical systems: description, models and applications}, CONFERENCE_PLACE = {Pavia}, CONFERENCE_DATE = {2004}, } @TECHREPORT{BARONI_2004_TECHREPORT_BCLQU_157368, AUTHOR = {Baroni, P. and Calzolari, N. and Lenci, A. and Quochi, V. and Ulivieri, M.}, TITLE = {Final Resources Landscape}, YEAR = {2004}, ABSTRACT = {ELSNET-4 Deliverable D6.4}, KEYWORDS = {Language Resources, Landscapes}, PAGES = {11}, URL = {https://publications.cnr.it/doc/157368}, } @TECHREPORT{BARONI_2004_TECHREPORT_BCM_157371, AUTHOR = {Baroni, P. and Calzolari, N. and Mammini, M.}, TITLE = {Final Resources Roadmap}, YEAR = {2004}, ABSTRACT = {ELSNET-4 Deliverable D6.3}, KEYWORDS = {Language Resources, Roadmaps}, URL = {https://publications.cnr.it/doc/157371}, } @TECHREPORT{KRAUWER_2004_TECHREPORT_KCB_157394, AUTHOR = {Krauwer, S. and Calzolari, N. and Busemann, S.}, TITLE = {The ELSNET Roadmap for Language and Speech Technology}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/157394}, } @ARTICLE{CALZOLARI_2003_ARTICLE_C_64472, AUTHOR = {Calzolari, N.}, TITLE = {Corpus-based lexicon building: an overview across projects, problems, approaches}, YEAR = {2003}, ABSTRACT = {Abstract - The paper aims at providing an overview of the current situation with respect to the interaction between two different but connected language resources, i.e. lexicons and corpora. The connection has become more and more evident in the field of natural language processing in the last years owing to a series of converging factors, such as the availability of increasingly larger on-line corpora, the trend to use corpus evidence in “printed” lexicography, the presence of more robust automatic tools for corpus analysis, annotation, and extraction of information, the need for computational lexicons to adhere to real usage of language as evidenced in corpora. I shall illustrate some issues regarding the corpus-lexicon relation as it emerges in particular from several representative European projects regarding both the construction of large-scale harmonised resources to be used for various applicative purposes, also of multilingual nature, and the acquisition of lexical information from corpora to enhance and tune existing lexicons. I conclude by hinting at a few issues, related to corpus-lexicon interaction, to be considered a priority in the near future.}, PAGES = {79-116}, URL = {https://publications.cnr.it/doc/64472}, VOLUME = {16-17}, } @ARTICLE{CALZOLARI_2003_ARTICLE_C_64482, AUTHOR = {Calzolari, N.}, TITLE = {Trattamento Automatico della Lingua e Risorse Linguistiche}, YEAR = {2003}, PAGES = {84-89}, URL = {https://publications.cnr.it/doc/64482}, VOLUME = {XXI}, } @ARTICLE{CALZOLARI_2003_ARTICLE_C_64498, AUTHOR = {Calzolari, N.}, TITLE = {"Antonio Zampolli. Una vita per la Linguistica Computazionale"}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/64498}, VOLUME = {2}, } @ARTICLE{CALZOLARI_2003_ARTICLE_CB_64459, AUTHOR = {Calzolari, N. and Bindi, R.}, TITLE = {Acquisition of lexical information from a large textual Italian corpus}, YEAR = {2003}, ABSTRACT = {information others than those usually found in machine readable dictionaries or manually encoded by lexicographers are urgently needed. Different sources must be exploited if we want to overcome the “lexical bottleneck” of Natural Language Processing. Very interesting data can be found by processing large textual corpora, where the actual usage of the language can be truly investigated. These data refer, typically, to various kinds of syntagmatic relations, which are particularly problematic in many NLP applications. The paper describes how this data can be at least partially extracted by processing and analysing large text corpora, with quantitative/statistic methods. We describe two types of quantitative analyses whose aim is to extract information on the strength of association between two words, and on fixed phrases and idioms. We observe how the measure of the association ratio provides quantitative evidence to a number of lexical, syntactic and semantic relationships between word-pairs. One of the claims is that the linguistic information embodied in all these quite different types of lexical collocations can be helpful for lexical disambiguation in analysis and crucial for lexical selection in generation. This is a step towards a more objective lexicography and a more “data-based” linguistics.}, PAGES = {117-131}, URL = {https://publications.cnr.it/doc/64459}, VOLUME = {16-17}, } @ARTICLE{LENCI_2003_ARTICLE_LCZ_64475, AUTHOR = {Lenci, A. and Calzolari, N. and Zampolli, A.}, TITLE = {SIMPLE: plurilingual semantic lexicons for natural language processing}, YEAR = {2003}, PAGES = {323-352}, URL = {https://publications.cnr.it/doc/64475}, VOLUME = {16-17}, } @ARTICLE{MARINELLI_2003_ARTICLE_MBBGMOPRCZ_64468, AUTHOR = {Marinelli, R. and Biagini, L. and Bindi, R. and Goggi, S. and Monachini, M. and Orsolini, P. and Picchi, E. and Rossi, S. and Calzolari, N. and Zampolli, A.}, TITLE = {The Italian PAROLE corpus: an overview}, YEAR = {2003}, PAGES = {401-421}, URL = {https://publications.cnr.it/doc/64468}, VOLUME = {16-17}, PUBLISHER = {Giardini editori e stampatori (Pisa, Italia)}, ISSN = {0392-6907}, JOURNAL = {Linguistica computazionale (Testo stamp.)}, } @ARTICLE{MONACHINI_2003_ARTICLE_MC_64489, AUTHOR = {Monachini, M. and Calzolari, N.}, TITLE = {Methods for standardization: the case of morphosyntax within the EAGLES project}, YEAR = {2003}, PAGES = {423-460}, URL = {https://publications.cnr.it/doc/64489}, VOLUME = {16-17}, PUBLISHER = {Giardini editori e stampatori (Pisa, Italia)}, ISSN = {0392-6907}, JOURNAL = {Linguistica computazionale (Testo stamp.)}, } @ARTICLE{MONTEMAGNI_2003_ARTICLE_MBBCCLPZFMRBPSZMPD_64477, AUTHOR = {Montemagni, S. and Barsotti, F. and Battista, M. and Calzolari, N. and Corazzari, O. and Lenci, A. and Pirrelli, V. and Zampolli, A. and Fanciulli, F. and Massetani, M. and Raffaelli, R. and Basili, R. and Pazienza, M. T. and Saracino, D. and Zanzotto, F. and Mana, N. and Pianesi, F. and Delmonte, R.}, TITLE = {The syntactic-semantic Treebank of Italian. An Overview}, YEAR = {2003}, PAGES = {461-492}, URL = {https://publications.cnr.it/doc/64477}, VOLUME = {16-17}, } @ARTICLE{ROVENTINI_2003_ARTICLE_RABCCGMMSZ_64479, AUTHOR = {Roventini, A. and Alonge, A. and Bertagna, F. and Calzolari, N. and Cancila, J. and Girardi, C. and Magnini, B. and Marinelli, R. and Speranza, M. and Zampolli, A.}, TITLE = {ItalWordNet: building a large semantic database for the automatic treatment of Italian}, YEAR = {2003}, ABSTRACT = {Abstract - This paper describes the main characteristics of the ItalWordNet semantic database, built in the context of the SI-TAL Italian National Project, within which a set of integrated resources and tools for the automatic treatment of the Italian language was realized. The database was created by extending the Italian wordnet developed within the EuroWordNet project, by adding: i) adjectives, adverbs and proper nouns (not dealt with in EuroWordNet); ii) a terminological subset related to the economic-financial domain. The relevant changes involved by these extensions both in the linguistic model and in the data structure are also illustrated. In particular, we discuss: i) the overall architecture of the database; ii) the semantic relations used to encode information on synsets; iii) the changes made to the EuroWordNet Top Ontology structure; iv) the specific characteristics of the terminological subset and the solutions adopted to link it to the generic wordnet. Keywords - synset, semantic database, wordnet, semantic}, KEYWORDS = {Database lessicale, Rete semantica, Relazioni semantiche, Risorse linguistiche}, PAGES = {745-791}, URL = {https://publications.cnr.it/doc/64479}, VOLUME = {18-19}, } @ARTICLE{RUIMY_2003_ARTICLE_RCGSCZ_64469, AUTHOR = {Ruimy, N. and Corazzari, O. and Gola, E. and Spanu, A. and Calzolari, N. and Zampolli, A.}, TITLE = {The PAROLE model and the Italian Syntactic lexicon}, YEAR = {2003}, ABSTRACT = {Abstract - This paper presents an overview of a large scale Syntactic Computational Lexicon of Italian. This lexicon was elaborated in the framework of the EC funded LE-PAROLE project, which developed core, generic and re-usable written language resources in 12 EU languages. All monolingual lexica were built according to the same design principles, same linguistic specifications and representation format. The PAROLE Italian lexicon is representative of modern Italian language use. The entries were selected on a frequency basis from the ILC Corpus and the syntactic structures encoded were partly inferred from their contexts of occurrence. Both the general structure of a PAROLE lexicon and the specificity of its Italian instantiation are presented. Some languagespecific linguistic and lexicographic options concerning crucial issues to a lexicon building process are illustrated. An overview of the syntactic structures encoded for verbs, nouns and adjectives allows lexicon syntactic coverage as well as description fine-grainedness to be estimated.}, PAGES = {793-820}, URL = {https://publications.cnr.it/doc/64469}, VOLUME = {18-19}, PUBLISHER = {Giardini editori e stampatori (Pisa, Italia)}, ISSN = {0392-6907}, JOURNAL = {Linguistica computazionale (Testo stamp.)}, } @ARTICLE{RUIMY_2003_ARTICLE_RMGCDUR_64485, AUTHOR = {Ruimy, N. and Monachini, M. and Gola, E. and Calzolari, N. and Del Fiorentino, M. C. and Ulivieri, M. and Rossi, S.}, TITLE = {A computational semantic lexicon of Italian: SIMPLE}, YEAR = {2003}, ABSTRACT = {Abstract - This paper describes the Italian Semantic Computational Lexicon elaborated in the framework of the European LE-SIMPLE Project. SIMPLE was aimed at adding a layer of semantic information to a subset of PAROLE lexica. The SIMPLE framework is based principally on the Generative Lexicon theory which allows to express the multidimensionality of meaning by means of ‘qualia structure’. Word senses are described according to their position within the SIMPLE ontology, which is based on the principle of orthogonal inheritance and consists of semantic types for characterizing simple nouns, event and property denoting lexical units. The encoding process is guided by templates, that are schematic structures containing clusters of structured information specific to each semantic type. Besides a high degree of granularity of meaning representation, the SIMPLE lexicon presents innovative aspects such as link between the syntactic and semantic levels of information, description of predicative representation and enforcement of selectional restrictions/preferences on arguments.}, PAGES = {821-864}, URL = {https://publications.cnr.it/doc/64485}, VOLUME = {18-19}, PUBLISHER = {Giardini editori e stampatori (Pisa, Italia)}, ISSN = {0392-6907}, JOURNAL = {Linguistica computazionale (Testo stamp.)}, } @ARTICLE{ZAMPOLLI_2003_ARTICLE_ZCC_64496, AUTHOR = {Zampolli, A. and Calzolari, N. and Cignoni, L.}, TITLE = {Foreword}, YEAR = {2003}, PAGES = {xiii-xv}, URL = {https://publications.cnr.it/doc/64496}, VOLUME = {16-17}, } @BOOK{ZAMPOLLI_2003_BOOK_ZCC_136418, AUTHOR = {Zampolli, A. and Calzolari, N. and Cignoni, L.}, TITLE = {Computational Linguistics in Pisa-Linguistica Computazionale a Pisa}, YEAR = {2003}, KEYWORDS = {Linguistica Comput, Tecnologie linguist, NLP, Risorse Linguistiche, Applicazioni Ling}, URL = {https://publications.cnr.it/doc/136418}, } @INCOLLECTION{CALZOLARI_2003_INCOLLECTION_CZ_136431, AUTHOR = {Calzolari, N. and Zampolli, A.}, TITLE = {The EAGLES/ISLE Initiative for Setting Standards: the Computational Lexicon Working Group for Multilingual Lexicons}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/136431}, } @INCOLLECTION{CALZOLARI_2003_INCOLLECTION_CZL_136421, AUTHOR = {Calzolari, N. and Zampolli, A. and Lenci, A.}, TITLE = {Risorse linguistiche per un accesso al 'contenuto'}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/136421}, PUBLISHER = {Angeli (Milano, ITA)}, } @INCOLLECTION{MONTEMAGNI_2003_INCOLLECTION_MBBCCLZRPMD_136422, AUTHOR = {Montemagni, S. and Barsotti, F. and Battista, M. and Calzolari, N. and Corazzari, O. and Lenci, A. and Zampolli, A. and Raffaelli, R. and Pazienza, M. T. and Mana, N. and Delmonte, R.}, TITLE = {Building the Italian Syntactic-Semantic Treebank}, YEAR = {2003}, KEYWORDS = {Corpora testuali, Annot. sintattica, Annot. semantica, Treebank}, URL = {https://publications.cnr.it/doc/136422}, } @INPROCEEDINGS{BUITELAR_2003_INPROCEEDINGS_BDCL_84550, AUTHOR = {Buitelar, P. and Declerck, T. and Calzolari, N. and Lenci, A.}, TITLE = {Language Resources and the Semantic Web}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84550}, CONFERENCE_NAME = {ENABLER/ELSNET Workshop International Roadmap for Language Resources}, CONFERENCE_PLACE = {Utrecht}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{BUITELAR_2003_INPROCEEDINGS_BDCL_84551, AUTHOR = {Buitelar, P. and Declerck, T. and Calzolari, N. and Lenci, A.}, TITLE = {Towards a Language Infrastructure for the Semantic Web}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84551}, CONFERENCE_NAME = {ISWC2003 Workshop on Human Language Technology for the Semantic Web and Web Sercives}, CONFERENCE_PLACE = {Sanibel Island, Florida}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_84552, AUTHOR = {Calzolari, N.}, TITLE = {Towards a Gateway between Language Resources and Knowledge Resources}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84552}, CONFERENCE_NAME = {International Conference on Natural Language Processing and Knowledge Engineering}, CONFERENCE_PLACE = {Beijing (Cina)}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_84553, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources in the Semantic Web Vision}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84553}, CONFERENCE_NAME = {International Conference on Natural Language Processing and Knowledge Engineering}, CONFERENCE_PLACE = {Beijing (Cina)}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_84554, AUTHOR = {Calzolari, N.}, TITLE = {Lexicons and Corpora: between Theory and Practice}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84554}, CONFERENCE_NAME = {VIII Simposio Internacional de Comunicacion Social}, CONFERENCE_PLACE = {Santiago de Cuba}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_84555, AUTHOR = {Calzolari, N.}, TITLE = {Risorse Linguistiche per la lingua italiana scritta}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84555}, CONFERENCE_NAME = {Conferenza TIPI-Tecnologie Informatiche nella Promozione della Lingua Italiana}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_84557, AUTHOR = {Calzolari, N.}, TITLE = {A State of Art in Computational Linguistics and Language Resources for Language Technology}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84557}, CONFERENCE_NAME = {XVII International Congress of Linguists}, CONFERENCE_PLACE = {Prague}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_CBLM_84556, AUTHOR = {Calzolari, N. and Bertagna, F. and Lenci, A. and Monachini, M.}, TITLE = {New Perspectives for Lexical Resources in the Semantic Web Scenario}, YEAR = {2003}, PAGES = {10-19}, URL = {https://publications.cnr.it/doc/84556}, CONFERENCE_NAME = {GL 2003-Second International Workshop on Generative Approaches to the Lexicon}, CONFERENCE_PLACE = {Genève, Switzerland}, CONFERENCE_DATE = {15-17 May 2003}, EDITOR = {Bouillon, P. and Kanzaki, K.}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_CLQ_84547, AUTHOR = {Calzolari, N. and Lenci, A. and Quochi, V.}, TITLE = {Towards Multiword and Multilingual Lexicons: Between Theory and Practice}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84547}, CONFERENCE_NAME = {Linguistics and Phonetics 2002 Conference}, CONFERENCE_PLACE = {Urayasu (Giappone)}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{IDE_2003_INPROCEEDINGS_ILC_84561, AUTHOR = {Ide, N. and Lenci, A. and Calzolari, N.}, TITLE = {RDF Instantiation of ISLE/MILE Lexical Entries}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84561}, CONFERENCE_NAME = {ACL 2003 Workshop on Linguistic Annotation: Getting the Model Right}, CONFERENCE_PLACE = {Sapporo}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{RUIMY_2003_INPROCEEDINGS_RMC_84563, AUTHOR = {Ruimy, N. and Monachini, M. and Calzolari, N.}, TITLE = {Un lexique électronique multi-niveaux de l'italien}, YEAR = {2003}, ABSTRACT = {CLIPS est la plus vaste ressource lexicale électronique de l'italien. Elle comprend 55.000 mots codés à 4 niveaux de description linguistique. La représentation lexicale est basée sur des standards internationaux: CLIPS utilise en effet le même modèle, le même langage de représentation et la même méthodologie que 11 autres lexiques développés au cours des projets européens PAROLE et SIMPLE. Les informations fournies, particulièrement utiles pour des applications de TLH, sont très structurées, granulaires et innovatrices, avec entre autres au niveau sémantique la Extended Qualia Structure, basée sur la théorie du Lexique Génératif, et la représentation prédicative. La description d'une unité lexicale est un continuum à travers les différents niveaux d'information. Les propriétés phonologiques, morphologiques et syntaxiques d'un lemme, ainsi que son/ses schéma(s) d'arguments sont décrits. Au niveau sémantique, chaque lexème/sens est associé à un vaste ensemble structuré d'informations, parmi lesquelles son type ontologique et l'expression - au moyen des relations qualia - des différentes facettes de sa sémantique. La représentation prédicative décrit, quant à elle, le scénario sémantique (dans lequel le mot s'insère) et ses participants auxquels sont attribués rôle thématique et contraintes sémantiques. La relation des niveaux syntaxique et sémantique est assurée par des liens permettant de projeter les structures argumentales sur leur(s) réalisation(s) syntaxique(s). Une telle richesse d'information, et en particulier celle fournie par la Extended Qualia, permet notamment 1) de constituer des réseaux sémantiques, en formulant une requête sur l'ensemble des relations qualia contenant un mot-clé ; 2) d'extraire des noyaux de vocabulaire de domaines spécifiques, en alternant requêtes sur qualia et sens ; 3) d'acquérir des collocations lexicales, en exploitant les liens syntagmatiques évènements/entités exprimés par les qualia ; 4) de désambiguïser la contribution sémantique du modificateur dans certains groupes nominaux complexes, en analysant la structure qualia de la tête.}, PAGES = {1-10}, URL = {https://publications.cnr.it/doc/84563}, ISBN = {80-86732-21-5}, CONFERENCE_NAME = {CIL XVII International Congress of Linguists}, CONFERENCE_PLACE = {Prague}, CONFERENCE_DATE = {24-29 Luglio 2003}, } @INPROCEEDINGS{SORIA_2003_INPROCEEDINGS_SBC_84564, AUTHOR = {Soria, C. and Bertagna, F. and Calzolari, N.}, TITLE = {ItalWordNet in an annotation task: a chance for discussion}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/84564}, CONFERENCE_NAME = {First International WordNet Conference, Global WordNet Association}, CONFERENCE_PLACE = {Mysore}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_112894, AUTHOR = {Calzolari, N.}, TITLE = {Tecnologie della lingua}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/112894}, CONFERENCE_NAME = {Tecnologie della Lingua: strategie, politica e mercato}, CONFERENCE_PLACE = {Firenze}, CONFERENCE_DATE = {2003}, } @INPROCEEDINGS{CALZOLARI_2003_INPROCEEDINGS_C_112895, AUTHOR = {Calzolari, N.}, TITLE = {Verso una nuova generazione di risorse lessicali e la cooperazione internazionale}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/112895}, CONFERENCE_NAME = {Actas del Tercero Seminario de la Escuela Interlatina de Altos Estudios en Lingüística Aplicada}, CONFERENCE_PLACE = {San Millán de la Cogolla}, CONFERENCE_DATE = {2003}, } @TECHREPORT{ALLEGRINI_2003_TECHREPORT_ACMMHIGCDP_157348, AUTHOR = {Allegrini, P. and Calzolari, N. and Marchi, S. and Montemagni, S. and Hepple, M. and Ireson, N. and Gomez Hidalgo, J. M. and Carrero Garcia, F. and De Buenaga Rodriguez, M. and Puera Sanz, E.}, TITLE = {POESIA Lexical Resources and Tools for Each Language}, YEAR = {2003}, ABSTRACT = {The aim of this report is to review the various resources that the different language processing sites expect to use in the development of their language-specific text filtering components. Some of the required resources are ones that were developed before Poesia, possibly by one the Poesia partners, or possibly elsewhere but being now in the public domain. Such resources may require adaptation to the Poesia task. Other resources required for Poesia will be developed as part of the project. In some cases, this development has already been done or is in progress, whilst in others, it is yet to be undertaken. In what follows, the status of each of the resources described will be made clear in terms of these alternatives.}, KEYWORDS = {Lexical Resources, nlp}, PAGES = {30}, URL = {https://publications.cnr.it/doc/157348}, } @TECHREPORT{BARONI_2003_TECHREPORT_BCF_157346, AUTHOR = {Baroni, P. and Calzolari, N. and Fiorentini, G.}, TITLE = {Reources Roadmatp (1st release)}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157346}, } @TECHREPORT{BARONI_2003_TECHREPORT_BCF_317098, AUTHOR = {Baroni, P. and Calzolari, N. and Fiorentini, G.}, TITLE = {Resources Roadmap (First Release)}, YEAR = {2003}, ABSTRACT = {ELSNET-4 Deliverable D6.1}, KEYWORDS = {Language Resources, Roadmaps}, URL = {https://publications.cnr.it/doc/317098}, } @TECHREPORT{BARONI_2003_TECHREPORT_BCFLM_157347, AUTHOR = {Baroni, P. and Calzolari, N. and Fiorentini, G. and Lenci, A. and Monachini, M.}, TITLE = {Resources Landscape Map (1st release)}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157347}, } @TECHREPORT{BARONI_2003_TECHREPORT_BCFLM_317185, AUTHOR = {Baroni, P. and Calzolari, N. and Fiorentini, G. and Lenci, A. and Monachini, M.}, TITLE = {Resources Landscape (First Release)}, YEAR = {2003}, ABSTRACT = {ELSNET-4 Deliverable D6.2}, KEYWORDS = {Language Resources, Landscapes}, URL = {https://publications.cnr.it/doc/317185}, } @TECHREPORT{BARONI_2003_TECHREPORT_BCL_157313, AUTHOR = {Baroni, P. and Calzolari, N. and Lenci, A.}, TITLE = {Extended Configuration of the Network and Final Report}, YEAR = {2003}, ABSTRACT = {ENABLER Deliverable D1.2}, KEYWORDS = {Language Resources, Networks}, PAGES = {21}, URL = {https://publications.cnr.it/doc/157313}, } @TECHREPORT{BERTAGNA_2003_TECHREPORT_BCLM_157314, AUTHOR = {Bertagna, F. and Calzolari, N. and Lenci, A. and Monachini, M.}, TITLE = {Report on the Feasibility and the Organisational Requirements for the Construction of Multilingual LRs}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157314}, } @TECHREPORT{BIRD_2003_TECHREPORT_BHNRCA_157315, AUTHOR = {Bird, S. and Hovy, E. and Nerbonne, J. and Rosner, M. and Calzolari, N. and Arnold, D.}, TITLE = {ACL Anthology-A Digital Archive of Research Papers in Computational Linguistics}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157315}, } @TECHREPORT{CALZOLARI_2003_TECHREPORT_CBLM_157316, AUTHOR = {Calzolari, N. and Bertagna, F. and Lenci, A. and Monachini, M.}, TITLE = {Standards and Best Practice for Multilingual Computational Lexicons-MILE (the Multilingual ISLE Lexical Entry)}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157316}, } @TECHREPORT{CALZOLARI_2003_TECHREPORT_CBLM_157337, AUTHOR = {Calzolari, N. and Bertagna, F. and Lenci, A. and Monachini, M.}, TITLE = {MILE Users? Evaluation and Feedback}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157337}, } @TECHREPORT{CALZOLARI_2003_TECHREPORT_CGP_157339, AUTHOR = {Calzolari, N. and Grishman, R. and Palmer, M.}, TITLE = {Introduction to the CLWG Guidelines}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157339}, } @TECHREPORT{CALZOLARI_2003_TECHREPORT_CMPZ_157344, AUTHOR = {Calzolari, N. and McNaught, J. and Palmer, M. and Zampolli, A.}, TITLE = {ISLE Final Report}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157344}, } @TECHREPORT{CALZOLARI_2003_TECHREPORT_CW_157317, AUTHOR = {Calzolari, N. and Wittenburg, P.}, TITLE = {Report of the ISO Preparation Workhop on Lexicons}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157317}, } @TECHREPORT{GAVRILIDOU_2003_TECHREPORT_GDLCMS_157321, AUTHOR = {Gavrilidou, M. and Desipri, E. and Labropoulo, P. and Calzolari, N. and Monachini, M. and Soria, C.}, TITLE = {Technical Specifications for the Selection and Encoding of Multilingual Resources}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157321}, } @TECHREPORT{LENCI_2003_TECHREPORT_LCM_157345, AUTHOR = {Lenci, A. and Calzolari, N. and Monachini, M.}, TITLE = {Report on LR Related Activities to Be Promoted}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157345}, } @TECHREPORT{MONACHINI_2003_TECHREPORT_MBCL_157322, AUTHOR = {Monachini, M. and Bertagna, F. and Calzolari, N. and Lenci, A.}, TITLE = {Improving Harmonisation between Resources: Divergence/Convergence between Specifications and de-facto Standards}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157322}, } @TECHREPORT{MONACHINI_2003_TECHREPORT_MBCUN_157323, AUTHOR = {Monachini, M. and Bertagna, F. and Calzolari, N. and Underwood, N. and Navarretta, C.}, TITLE = {Towards a Standard for the Creation of Lexica}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157323}, } @TECHREPORT{RUIMY_2003_TECHREPORT_RMC_157325, AUTHOR = {Ruimy, N. and Monachini, M. and Calzolari, N.}, TITLE = {Progetto CLIPS: Specifiche Linguistiche e Manuale di Codifica, Livello sintattico}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157325}, } @TECHREPORT{RUIMY_2003_TECHREPORT_RMC_157326, AUTHOR = {Ruimy, N. and Monachini, M. and Calzolari, N.}, TITLE = {Progetto CLIPS: Specifiche Linguistiche e Manuale di Codifica, Livello semantico}, YEAR = {2003}, URL = {https://publications.cnr.it/doc/157326}, } @ARTICLE{CALZOLARI_2002_ARTICLE_C_64455, AUTHOR = {Calzolari, N.}, TITLE = {Written Language Resources at LREC in Las Palmas: Closing Session}, YEAR = {2002}, URL = {https://publications.cnr.it/doc/64455}, } @ARTICLE{CALZOLARI_2002_ARTICLE_CSBB_64500, AUTHOR = {Calzolari, N. and Soria, C. and Bertagna, F. and Barsotti, F.}, TITLE = {Evaluating Lexical Resources Using Senseval}, YEAR = {2002}, ABSTRACT = {The aim of our paper is twofold: to introduce some general reflections on the task of lexical semantic annotation and the adequacy of existing lexical-semantic reference resources, while giving an overall description of the Italian lexical sample task for the SENSEVAL-2 experiment. We suggest how the SENSEVAL exercise (and comparison between the two editions of the experiment) can be employed to evaluate the lexical reference resources used for annotation. We conclude with a few general remarks on the gap between the lexicon, a partially decontextualised object, and the corpus, where context plays a significant role.}, KEYWORDS = {Risorse Lessicali, Disambiguazione, Semantica, Annotazione, Wordnet}, PAGES = {375-390}, URL = {https://publications.cnr.it/doc/64500}, VOLUME = {8}, DOI = {10.1017/S1351324902003017}, PUBLISHER = {Cambridge University Press (Cambridge, Regno Unito)}, ISSN = {1469-8110}, JOURNAL = {Natural language engineering (Online)}, } @ARTICLE{CALZOLARI_2002_ARTICLE_CZL_30862, AUTHOR = {Calzolari, N. and Zampolli, A. and Lenci, A.}, TITLE = {Towards a Standard for a Multilingual Lexical Entry: The EAGLES/ISLE Initiative}, YEAR = {2002}, ABSTRACT = {ISLE, a transatlantic standard oriented initiative supported by EC and NSF under the Human Language Technology (HLT) programme, is a continuation of the long standing EAGLES initiative. The objective is to develop widely agreed and urgently demanded standards and guidelines for infrastructural language resources, tools, and HLT products. ISLE targets the areas of multilingual computational lexicons, natural interaction and multimodality, and evaluation. We describe the preliminary guidelines of a standard framework for multilingual computational lexicons, based on a general schema for the "Multilingual ISLE Lexical Entry" (MILE). The needs and features of existing Machine Translation systems provide the main reference points for the process of consensual definition of the MILE. We also provide a brief description of the EU SIMPLE semantic lexicons, built on the basis of previous EAGLES recommendations and now enlarged to real-size lexicons within national projects, thus creating a large infrastructural platform of harmonised lexicons in Europe. EAGLES previous results have already become de facto widely adopted standards, and EAGLES itself is a well-known trademark and point of reference for HLT projects and products.}, KEYWORDS = {Lessici multilingui, standard internazion, Semantic Web, Modello lessicale, Standard lessicali}, PAGES = {264-279}, URL = {https://publications.cnr.it/doc/30862}, VOLUME = {2276}, PUBLISHER = {Springer (Berlin, Germania)}, ISSN = {0302-9743}, JOURNAL = {Lecture notes in computer science}, } @BOOK{CALZOLARI_2002_BOOK_C_136411, AUTHOR = {Calzolari, N.}, TITLE = {Computational Lexicons and Corpus Analysis: Between Theory and Practice}, YEAR = {2002}, URL = {https://publications.cnr.it/doc/136411}, } @BOOK{CALZOLARI_2002_BOOK_C_136415, AUTHOR = {Calzolari, N.}, TITLE = {Computational Lexicons: Towards a New Paradigm of an Open Lexical Infrastructure?}, YEAR = {2002}, URL = {https://publications.cnr.it/doc/136415}, } @BOOK{CALZOLARI_2002_BOOK_C_136416, AUTHOR = {Calzolari, N.}, TITLE = {Language Resources in a Multilingual Setting: The European Perspective}, YEAR = {2002}, URL = {https://publications.cnr.it/doc/136416}, } @TECHREPORT{STARYNKEVITCH_2002_TECHREPORT_SDTZHIGACMMG_430635, AUTHOR = {Starynkevitch, B. and Daoudi, M. and Tombelle, C. and Zheng, H. and Hepple, M. and Ireson, N. and Gomez Hildago, J. and Allegrini, P. and Calzolari, N. and Marchi, S. and Montemagni, S. and Guerra, S.}, TITLE = {POESIA Software Architecture Definition Document}, YEAR = {2002}, ABSTRACT = {Software Architecture Definition Document}, KEYWORDS = {NLP, Software Engineering}, PAGES = {68-80}, URL = {https://publications.cnr.it/doc/430635}, } @ARTICLE{CALZOLARI_2001_ARTICLE_CCZ_30863, AUTHOR = {Calzolari, N. and Corazzari, O. and Zampolli, A.}, TITLE = {Lexical-Semantic Tagging of an Italian Corpus}, YEAR = {2001}, ABSTRACT = {Semantically tagged corpora are becoming an urgent need for training and evaluation within many applications. They are also the natural accompaniment of semantic lexicons, for which they constitute both a useful testbed to evaluate their adequacy and a repository of corpus examples for the attested senses. It is essential that sound criteria are defined for their construction and a specific methodology is set up for the treatment of various semantic phenomena. We present some observations and results concerning the lexical-semantic tagging of an Italian corpus within the framework of two projects: the ELSNET feasibility study, part of a preparatory phase started with Senseval/Romanseval, and an Italian National Project (TAL), where one of the components is the lexical-semantic annotation of larger quantities of texts for an Italian syntactic-semantic Treebank. The results of the ELSNET experiment have been of utmost importance for the definition of the technical guidelines for the lexical-semantic level of annotation of the Treebank.}, KEYWORDS = {Annotazione semantic, Corpus annotato, Treebank, Lessico semantico, Semantica}, PAGES = {291-304}, URL = {https://publications.cnr.it/doc/30863}, VOLUME = {2004}, PUBLISHER = {Springer (Berlin, Germania)}, ISSN = {0302-9743}, JOURNAL = {Lecture notes in computer science}, } @INCOLLECTION{BUSA_2001_INCOLLECTION_BCLP_136430, AUTHOR = {Busa, F. and Calzolari, N. and Lenci, A. and Pustejovsky, J.}, TITLE = {Building a Semantic Lexicon: Structuring and Generating Concepts}, YEAR = {2001}, KEYWORDS = {Semantica Lessicale, Lessico Generativo, Lessici computaziona, Ontologie, Conoscenza semantica}, URL = {https://publications.cnr.it/doc/136430}, } @TECHREPORT{BARNBROOK_1994_TECHREPORT_BCFHMPSS_446186, AUTHOR = {Barnbrook, G. and Calzolari, N. and Federici, S. and Hoelter, M. and Montemagni, S. and Peters, C. and Schnelle, H. and Sinclair, J.}, TITLE = {ET10/51-Deliverable 8: Evaluation Report}, YEAR = {1994}, ABSTRACT = {The objective of the work in Pisa has been to translate and produce instantiations of the syntactically parsed definitions of the Cobuild dictionary: provided by Birmingham in a Typed Feature Structure formalism. However, as described in Methodology above, our results have been produced at two different levels: intermediate results; final results in the form of TFS entries. In the following, we will discuss briefly the possible applications of these different results for the three user types recognized in the introduction to this section: i. Human user ii. Human user-assisted by the machine iii. The machine Obviously, the discussion here below refers entirely to the results that would be obtained once the parser has been applied to the whole dictionary.}, KEYWORDS = {Language, Computational linguistics, Formal Definitions and Theory}, PAGES = {38}, URL = {https://publications.cnr.it/doc/446186}, } @TECHREPORT{CALZOLARI_1994_TECHREPORT_CFMP_446200, AUTHOR = {Calzolari, N. and Federici, S. and Montemagni, S. and Peters, C.}, TITLE = {ET-10/51-Final Report: Par. 3-Extracting, representing and using syntactic-semantic information from cobuild definitions}, YEAR = {1994}, ABSTRACT = {In May 1992 a new research project brought together the authors of this report. With the help and support of several other people and institutions, they worked steadily for two years, trying to improve the design and building of machine-usable lexicons, for automatic translation and many other applications. The starting point was clear. Around 1989 Helmut Schnelle of the Ruhr-Universitat Bochum became interested in the way in which words were defined in a new kind of dictionary called Cobuild. He thought that since theywere couched in sentences of apparently ordinary English, and had distinctive and repetitive shapes according to their meanings, it should be possible to represent them in logical form by means of regular rules.}, KEYWORDS = {Language, Computational linguistics, Formal Definitions and Theory, Semantics}, PAGES = {162}, URL = {https://publications.cnr.it/doc/446200}, } @INPROCEEDINGS{PICCHI_1990_INPROCEEDINGS_PPC_452773, AUTHOR = {Picchi, E. and Peters, C. and Calzolari, N.}, TITLE = {A tool for the second language learner organizing bilingual dictionary data in an interactive workstation}, YEAR = {1990}, ABSTRACT = {The data contained in a conventional English/ ltalian, ltalian/ English dictionary, recorded in machine-readable form and coded for computer typesetting, have been parsed and organized in a database type structure on a persona! computer. The aim is to implement an interactive bilingual lexical workstation in order to offer the second language learner and user a tool which overcomes many of the restrictions traditionally imposed by the norma! organization of the printed bi/inguai dictionary and allows him to consult and exploit the lexical materia! 1n new ways.}, KEYWORDS = {Second language learner, Bilingual dictionary, Workstation}, PAGES = {334-344}, URL = {https://publications.cnr.it/doc/452773}, VOLUME = {44}, ISBN = {2-05-101079-X}, CONFERENCE_NAME = {15th International Conference A. L. L. C}, CONFERENCE_PLACE = {Jerusalem, Israel}, CONFERENCE_DATE = {5-9/06/1988}, EDITOR = {Choueka, Y.}, }