@ARTICLE{DELGRATTA_2022_ARTICLE_DDZBB_472290, AUTHOR = {Del Gratta, R. and Del Grosso, A. M. and Zenzaro, S. and Boschetti, F. and Bambaci, L.}, TITLE = {La Filologia come sistema dinamico}, YEAR = {2022}, ABSTRACT = {Introduciamo un approccio formale all'evoluzione del contenuto informativo veicolato da documenti umanistici, con particolare attenzione alla prospettiva filologica e alle problematiche tipiche ad essa connesse (studio della tradizione, confronto tra testimoni, selezione e scelta delle lezioni, edizione di un testo, etc). Proponiamo un modello matematico in grado di formalizzare diversi fenomeni complessi in vari ambiti di ricerca quali la Linguistica Computazionale, la Filologia Digitale e l'Ingegneria del Software, soprattutto quando questi vengono applicati all'analisi di documenti e testi di interesse storico-letterario.}, KEYWORDS = {computational philology, formal philology, digital humanities}, PAGES = {1-20}, URL = {https://umanisticadigitale.unibo.it/article/view/13684}, VOLUME = {13}, DOI = {10.6092/issn.2532-8816/13684}, ISSN = {2532-8816}, JOURNAL = {Umanistica Digitale}, } @INCOLLECTION{VAGIONAKIS_2022_INCOLLECTION_VDBBDMM_472291, AUTHOR = {Vagionakis, I. and Del Gratta, R. and Boschetti, F. and Baroni, P. and Del Grosso, A. M. and Mancinelli, T. and Monachini, M.}, TITLE = {'Cretan Institutional Inscriptions' Meets CLARIN-IT}, YEAR = {2022}, ABSTRACT = {This paper presents 'Cretan Institutional Inscriptions', a resource in the domain of Digital Epigraphy developed at the Ca' Foscari University of Venice and supported by CLARIN-IT as part of its actions addressed to initiatives, projects and events in the field of Social Sciences and Humanities. The paper begins with a brief outline of the project within which the resource was created and then goes into a more in-depth description of the main methodologies used to develop the resource (EpiDoc and EFES) and of their benefits. The paper then focuses on the cooperation of the project with the Venice Centre of Digital and Public Humanities and the Italian node of CLARIN, also illustrating the dockerization process applied to the resource hosted on the CLARIN-IT servers. Some desiderata for future developments are outlined as well. The paper ends with some remarks about the widening of CLARIN horizons towards Digital Epigraphy and on the role of its K-Centres in this respect.}, KEYWORDS = {Digital Epigraphy, Digital Classics, Ancient Greek, Crete, Institutions, Text Encoding Initiative, TEI, EpiDoc, EpiDoc Front-End Services, EFES, Virtual Language Observatory, Dockerization, ILC4CLARIN, CLARIN-IT, CLARIN}, PAGES = {139-150}, URL = {https://ecp.ep.liu.se/index.php/clarin/article/view/424/382}, VOLUME = {189}, DOI = {10.3384/9789179294441}, ISBN = {978-91-7929-444-1}, BOOKTITLE = {Selected Papers from the CLARIN Annual Conference 2021}, EDITOR = {Monachini, M. and Eskevich, M.}, } @INPROCEEDINGS{BOSCHETTI_2022_INPROCEEDINGS_BBDDGNZ_472289, AUTHOR = {Boschetti, F. and Burgassi, C. and Del Gratta, R. and Del Grosso, A. M. and Guadagnini, E. and Nahli, O. and Zenzaro, S.}, TITLE = {Il Laboratorio di Filologia Collaborativa e Cooperativa (CoPhiLab) del CNR-ILC: dati, strumenti, servizi e infrastrutture}, YEAR = {2022}, ABSTRACT = {Questo contributo illustra le attività e le risorse del Laboratorio di Filologia Collaborativa e Cooperativa (CoPhiLab) dell'Istituto di Linguistica Computazionale "A. Zampolli" del Consiglio Nazionale delle Ricerche (CNR-ILC), con particolare attenzione all'uso delle infrastrutture di ricerca nazionali e internazionali.}, KEYWORDS = {Filologia Computazionale, Modelli Formali, Lingua Araba, Domain-Specific Languages, Ingegneria del Software}, PAGES = {45-50}, URL = {https://www.eventi.garr.it/it/conf22}, DOI = {10.26314/GARR-Conf22-proceedings}, PUBLISHER = {Associazione Consortium GARR (Roma, ITA)}, ISBN = {978-88-946629-1-7}, CONFERENCE_NAME = {CondiVisioni. La rete come strumento per costruire il futuro}, CONFERENCE_PLACE = {Palermo}, CONFERENCE_DATE = {18/05/2022-20/05/2022}, BOOKTITLE = {CONDIVISIONI La rete come strumento per costruire il futuro}, EDITOR = {Mieli, M. and Volpe, C.}, } @MISC{DELGRATTA_2022_MISC_D_471685, AUTHOR = {Del Gratta, R.}, TITLE = {Installing and configuring CLARIN-DSPACE on UBUNTU 22. 04 LTS}, YEAR = {2022}, ABSTRACT = {Il Manuale tecnico descrive le varie procedure per installare iò software CLARIN-DSPACE presso l'Istituto di Linguistica Computazionale}, KEYWORDS = {CLARIN, CLARIN-DSPACE, Repository, Installation Guide}, PAGES = {1-67}, URL = {https://publications.cnr.it/doc/471685}, } @ARTICLE{DELGRATTA_2021_ARTICLE_DBBS_461498, AUTHOR = {Del Gratta, R. and Boschetti, F. and Bambaci, L. and Sarnari, F.}, TITLE = {Document analysis and Textual philology: A Formal Perspective}, YEAR = {2021}, ABSTRACT = {We introduce a formal approach to document and text analysis. The method proposed herein results in a mathematical model/framework which can formalize different challenges in research fields such as computational linguistics, digital philology, and software engineering, principally if applied to document and text analysis. We examine texts and documents from an evolutionary perspective, where both corruption and correction are involved. We describe document evolution via fibre bundles formalism. We also provide other examples to demonstrate the capabilities of the model.}, KEYWORDS = {Formal model, document analysis, evolutionary approach, fibre bundles}, PAGES = {5-15}, URL = {https://www.innove.org/ijist/index.php/ijist/article/view/192}, VOLUME = {5}, PUBLISHER = {[El Mohajir Mohammed] ([S. l. ], Marocco)}, ISSN = {2550-5114}, JOURNAL = {International Journal of Information Science and Technology}, } @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)}, } @ARTICLE{MUGELLI_2021_ARTICLE_MBBDKT_461550, AUTHOR = {Mugelli, G. and Boschetti, F. and Bellandi, A. and Del Gratta, R. and Khan, A. F. and Taddei, A.}, TITLE = {Annotating ritual in ancient greek tragedy: A bottom-up approach in action}, YEAR = {2021}, ABSTRACT = {EuporiaRAGT is one of the pilot projects that adopt the Euporia system as a digital support to an historico-anthropological research on the form and function of rituals in the texts of ancient Greek tragedy. This paper describes the bottom-up approach adopted in the project: During the annotation stage, performed with a Domain Specific Language designed with a usercentred approach, the domain expert can annotate ritual and religious phenomena, with the possibility of registering different textual and interpretive variants; the design of a search engine, in a second phase of the work, allows the database to be tested and reorganized. Finally, the construction of an ontology allows to structure the tags, in order to perform complex queries on the database.}, KEYWORDS = {digital philology, dsl, ancient Greek}, PAGES = {17}, URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-85117031943\&origin=inward}, VOLUME = {15}, PUBLISHER = {Alliance of Digital Humanities Organizations ([Providence, RI?], Stati Uniti d'America)}, ISSN = {1938-4122}, JOURNAL = {Digital humanities quarterly}, } @INPROCEEDINGS{DELGRATTA_2021_INPROCEEDINGS_DBDB_472299, AUTHOR = {Del Gratta, R. and Boschetti, F. and Del Grosso, A. M. and Bambaci, L.}, TITLE = {La Filologia come sistema dinamico: qualche considerazione preliminare}, YEAR = {2021}, ABSTRACT = {In questo articolo introduciamo un approccio formale all'evoluzione dei documenti con particolare attenzione alla prospettiva filologica e alle problematiche tipiche connesse. Proponiamo un modello/framework matematico in grado di formalizzare diversi fenomeni complessi in vari ambiti di ricerca quali la Linguistica Computazionale, la Filologia Digitale e l'Ingegneria del Software, in particolare quando questa viene applicata all'analisi di documenti e testi di interesse storico-letterario.}, KEYWORDS = {approccio evoluzionistico, modello formale, analisi documentale e testuale, sistema dinamico, filologia computazionale}, PAGES = {484-490}, URL = {http://amsacta.unibo.it/6712/1/AIUCD2021_BOA-versione3A.pdf#page=500}, VOLUME = {aiucd2021}, DOI = {10.6092/unibo/amsacta/6712}, ISBN = {9788894253559}, CONFERENCE_NAME = {AIUCD 2021-DH per la società: e-guaglianza, partecipazione, diritti e valori nell'era digitale-DHs for society: e-quality, participation, rights and values in the Digital Age}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {19/01/2021-22/01/2021}, BOOKTITLE = {AIUCD 2021-DH per la società: e-guaglianza, partecipazione, diritti e valori nell'era digitale-DHs for society: e-quality, participation, rights and values in the Digital Age. Book of extended abstracts of the 10th national conference}, } @INPROCEEDINGS{KELLI_2021_INPROCEEDINGS_KLKVLBMHDVTV_462357, AUTHOR = {Kelli, A. and Lindén, K. and Kamocki, P. and Vider, K. and Labropoulou, P. and Birštonas, R. and Mantrov, V. and Hannesschläger, V. and Del Gratta, R. and Värv, A. and Tavits, G. and Vutt, A.}, TITLE = {The Interplay of Legal Regimes of Personal Data, Intellectual Property and Freedom of Expression in Language Research}, YEAR = {2021}, ABSTRACT = {Sometimes legal scholars get relevant but baffling questions from laypersons like: "The reference to a work is personal data, so does the GDPR actually require me to anonymise it? Or, as my voice data is personal data, does the GDPR automatically give me access to a speech recognizer using my voice sample? Or, can I say anything about myself without the GDPR requiring the web host to anonymise or remove the post? What can I say about others like politicians? And, what can researchers say about patients in a research report?" Based on these questions, the authors address the interaction of intellectual property and data protection law in the context of data minimisation and attribution rights, access rights, trade secret protection, and freedom of expression.}, KEYWORDS = {Legal aspects, research data}, PAGES = {154-159}, URL = {https://office.clarin.eu/v/CE-2021-1923-CLARIN2021_ConferenceProceedings.pdf}, CONFERENCE_NAME = {CLARIN Annual Conferece 2021}, CONFERENCE_DATE = {27-29/09/2021}, EDITOR = {Monachini, M. and Eskevich, M.}, } @INPROCEEDINGS{VAGIONAKIS_2021_INPROCEEDINGS_VDBBDMM_461540, AUTHOR = {Vagionakis, I. and Del Gratta, R. and Boschetti, F. and Baroni, P. and Del Grosso, A. M. and Mancinelli, T. and Monachini, M.}, TITLE = {'Cretan Institutional Inscriptions' Meets CLARIN-IT}, YEAR = {2021}, ABSTRACT = {This paper describes a project in the domain of Digital Epigraphy named 'Cretan Institutional Inscriptions' and developed at the Ca' Foscari University of Venice. The project is supported by CLARIN-IT as part of the actions addressed to initiatives, projects and events in the field of Humanities and Social Sciences. The main goal is to make the project visible through CLARIN channels with the hope that it will be a forerunner for other digital epigraphy projects in CLARIN. The article illustrates also the dockerization process applied to the 'Cretan Institutional Inscriptions' project, currently hosted on the CLARIN-IT servers.}, KEYWORDS = {Digital Epigraphy, Digital Classics, Ancient Greek, Crete, Institutions, Text Encoding Initiative, TEI, EpiDoc, EpiDoc Front-End Services, EFES, Virtual Language Observatory, Dockerization, ILC4CLARIN, CLARIN-IT, CLARIN}, PAGES = {48-53}, URL = {https://office.clarin.eu/v/CE-2021-1923-CLARIN2021_ConferenceProceedings.pdf}, CONFERENCE_NAME = {CLARIN Annual Conference 2021}, CONFERENCE_PLACE = {Virtual Edition}, CONFERENCE_DATE = {27-29/09/2021}, BOOKTITLE = {Proceedings of CLARIN Annual Conference 2021 (Virtual Edition)}, EDITOR = {Monachini, M. and Eskevich, M.}, } @INPROCEEDINGS{BOSCHETTI_2020_INPROCEEDINGS_BDMBMD_462360, AUTHOR = {Boschetti, F. and Del Gratta, R. and Monachini, M. and Buzzoni, M. and Monella, P. and Del Turco, R. R.}, TITLE = {"Tea for two": the Archive of the Italian Latinity of the Middle Ages meets the CLARIN infrastructure}, YEAR = {2020}, ABSTRACT = {This paper presents the Archive of the Italian Latinity of the Middle Ages (ALIM) and focuses, particularly, on its structure and metadata for its integration into the ILC4CLARIN repository. Access to this archive of Latin texts produced in Italy during the Middle Ages is of great importance in providing CLARIN-IT and the CLARIN community, at large, with critically reliable texts for the use of philologists, historians of literature, historians of institutions, culture and science of the Middle Ages.}, KEYWORDS = {Latin resources, CLARIN, corpus, repository}, PAGES = {121-125}, URL = {https://office.clarin.eu/v/CE-2020-1738-CLARIN2020_ConferenceProceedings.pdf}, CONFERENCE_NAME = {CLARIN Annual Conference 2020}, CONFERENCE_DATE = {05-07/10/2021}, } @INPROCEEDINGS{DELGRATTA_2020_INPROCEEDINGS_DBBS_462341, AUTHOR = {Del Gratta, R. and Boschetti, F. and Bambaci, L. and Sarnari, F.}, TITLE = {Approaching document analysis with a formal model}, YEAR = {2020}, ABSTRACT = {We introduce a formal approach to document and text analysis. The method proposed herein results in a mathematical and physical model/framework which can formalize different challenges in research fields such as computational linguistics, digital philology, and software engineering, principally if applied to document and text analysis. We examine texts and documents from an evolutionary perspective, where both corruption and correction are involved. We describe document evolution via fiber bundles formalism.}, KEYWORDS = {Formal model, document analysis, evolutionary approach}, PAGES = {208-214}, URL = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=9357202\&tag=1}, DOI = {10.1109/CIST49399.2021.9357202}, CONFERENCE_NAME = {6th International IEEE Colloquium on Information Science and Technology}, CONFERENCE_PLACE = {Agadir, Morocco}, CONFERENCE_DATE = {5-12/06/2021}, } @INPROCEEDINGS{BOSCHETTI_2020_INPROCEEDINGS_BDM_416444, AUTHOR = {Boschetti, F. and Del Gratta, R. and Monachini, M.}, TITLE = {Latin digital archives and research infrastructures: just a trendy option or a substantive need?}, YEAR = {2020}, ABSTRACT = {Latin digital archives and research infrastructures: just a trendy option or a substantive need?}, KEYWORDS = {Research Infrastructure, Digital Libraries, Latin}, URL = {https://publications.cnr.it/doc/416444}, CONFERENCE_NAME = {ALIM and beyond}, CONFERENCE_PLACE = {Venezia}, CONFERENCE_DATE = {27-28/01/2020}, } @ARTICLE{SPRUGNOLI_2019_ARTICLE_SPBD_403257, AUTHOR = {Sprugnoli, R. and Pardelli, G. and Boschetti, F. and Del Gratta, R.}, TITLE = {Un'Analisi Multidimensionale della Ricerca Italiana nel Campo delle Digital Humanities e della Linguistica Computazionale}, YEAR = {2019}, ABSTRACT = {This article proposes the first comparative study of four years of Italian conferences in the fields of Digital Humanities and Computational Linguistics. More specifically, we created a corpus consisting of the contributions presented in the AIUCD and CLiC-it conferences between 2014 and 2017 to which we applied a multidimensional analysis taking into consideration: (i) the study of collaborations between authors using social networks analysis techniques, (ii) the automatic extraction of terminology and information and (iii) the examination of citational practices. By combining both qualitative and quantitative methods of investigation, this paper aims to shed light on convergences and discrepancies between two research areas that historically have common origins.}, KEYWORDS = {Digital Humanities, Computational Linguistics, Comparative study}, PAGES = {59-89}, URL = {https://umanisticadigitale.unibo.it/article/view/8581}, VOLUME = {5}, DOI = {10.6092/issn.2532-8816/8581}, ISSN = {2532-8816}, JOURNAL = {Umanistica Digitale}, } @INPROCEEDINGS{ALBANESI_2019_INPROCEEDINGS_AD_414913, AUTHOR = {Albanesi, D. and Del Gratta, R.}, TITLE = {OpeNER and PANACEA: Web Services for the CLARIN Research Infrastructure}, YEAR = {2019}, ABSTRACT = {This paper describes the necessary steps for the integration of OpeNer and PANACEA Web Services within the CLARIN research infrastructure. The original Web Services are wrapped into a framework and re-implemented as REST APIs to be further exploited through both Language Resource Switchboard and WebLicht and made available for the CLARIN community.}, KEYWORDS = {CLARIN-IT, Interoperabilità, Research Infrastructure}, PAGES = {19-23}, URL = {https://office.clarin.eu/v/CE-2019-1512_CLARIN2019_ConferenceProceedings.pdf}, CONFERENCE_NAME = {CLARIN Annual Conference 2019}, CONFERENCE_PLACE = {Leipzig, Germany}, CONFERENCE_DATE = {30/09/2019, 02/10/2019}, } @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.}, } @INPROCEEDINGS{NICOLAS_2018_INPROCEEDINGS_NKMDCAEBQS_387361, AUTHOR = {Nicolas, L. and König, A. and Monachini, M. and Del Gratta, R. and Calamai, S. and Abel, A. and Enea, A. and Biliotti, F. and Quochi, V. and Stella, F. V.}, TITLE = {CLARIN-IT: State of Affairs, Challenges and Opportunities}, YEAR = {2018}, ABSTRACT = {his paper gives an overview on the Italian national CLARIN consortium as it currently stands two years after its creation at the end of 2015. It thus discusses the current state of affairs of the consortium on several aspects, especially with regards to members. It also discusses the events and initiatives that have been undertaken, as well as the ones that are planned in the close future. It finally outlines the conclusions of a user survey performed to understand the expectations of a targeted user population and provides indications regarding the next steps planned.}, KEYWORDS = {CLARIN-IT Consortium Pisa Bolzano Siena}, PAGES = {1-14}, URL = {http://www.ep.liu.se/ecp/contents.asp?issue=147}, VOLUME = {147}, ISBN = {978-91-7685-273-6}, CONFERENCE_NAME = {CLARIN Annual Conference 2017}, CONFERENCE_PLACE = {Budapest, Hungary}, CONFERENCE_DATE = {18-20 September, 2017}, BOOKTITLE = {Selected papers from the CLARIN Annual Conference 2017, Budapest, 18-20 September 2017}, } @INCOLLECTION{BOSCHETTI_2017_INCOLLECTION_BDD_382022, AUTHOR = {Boschetti, F. and Del Gratta, R. and Del Grosso, A. M.}, TITLE = {The role of digital scholarly editors in the design of components for cooperative philology}, YEAR = {2017}, ABSTRACT = {This contribution is focused on the role of the digital scholarly editor in the continuous process of analysis, development and evaluation of libraries of components for cooperative philology.}, KEYWORDS = {digital editions, collaborative and cooperative philology, digital philology}, PAGES = {249-253}, URL = {https://www.sidestone.com/books/advances-in-digital-scholarly-editing}, ISBN = {978-90-8890-484-4}, BOOKTITLE = {Advances in Digital Scholarly Editing}, EDITOR = {Boot, P. and Cappellotto, A. and Dillen, W. and Fischer, F. and Kelly, A. and Mertgens, A. and Sichani, A. and Spadini, E. and Van Hulle, D.}, } @INCOLLECTION{DELGRATTA_2017_INCOLLECTION_D_483914, AUTHOR = {Del Gratta, R.}, TITLE = {WordNets per lingue classiche}, YEAR = {2017}, ABSTRACT = {The Wordnet for Ancient Greek (AGWN) is presented and illustrated both as a stand-alone semantic net and as a participant in a more complex net of wordnets for historical and modern languages. Two applications of AGWN carried out within the Memorata Poetis project are described: in the first application, the AGWN is used to investigate multilingual synonyms; in the second one, AGWN is used to extract Greek synonyms in order to classify epigrams in terms of similar content.}, KEYWORDS = {WordNet, Perseus project, Ancient Greek Wordnet, oNLP, Classical Languages}, PAGES = {117-122}, URL = {https://publications.cnr.it/doc/483914}, VOLUME = {14/3}, DOI = {10.14277/6969-182-9/ANT-14-9}, PUBLISHER = {Edizioni Ca' Foscari (Venezia, ITA)}, ISBN = {978-88-6969-183-6}, BOOKTITLE = {Strumenti digitali e collaborativi per le Scienze dell'antichità}, EDITOR = {Mastandrea, P.}, } @INPROCEEDINGS{DELGRATTA_2017_INPROCEEDINGS_D_382031, AUTHOR = {Del Gratta, R.}, TITLE = {(Re)Using OpeNER and PANACEA Web Services in the CLARIN Research Infrastructure}, YEAR = {2017}, ABSTRACT = {We describe the implications of (re)using the OpeNer and PANACEA Web Services into the CLARIN Research Infrastructure. The analyzed tools are of great interest for specific communities such as academic and small business focused on sentiment/opinion analysis and on Machine Translation along with related technologies, but their outcomes may be of great importance for the CLARIN audience as well. In fact, the Virtual Language Observatory shows a lot of lexical resources for sentiment but a few tool, while a lot of lexical resources and tools are available for Machine Translation. This means that the latter community is already in CLARIN, while the former should be poked. If community-related challenges are on the political side, issues related to interoperability are definitely on the technical one. The initiative is carried out at the ILC4CLARIN center in Pisa, the leading one of the CLARIN-IT national Consortium. The least common multiple between those two projects is neither limited to tools and Web Services nor to the creation of annotated corpora and lexicons; neither to the focus they have on specific communities. They also are based on (and strongly pursue and suggest) the concept of interoperability. This is clear from the use of the Kyoto Annotation Format in OpeNer, of Graph Annotation Format in PANACEA8 and of and the Lexical Markup Framework in both. Data and tools interoperability is also a key asset in both CLARIN (https://www.clarin.eu/event/2017/clarin-workshop-towards-interoperability-lexico-semantic-resources) and EUDAT (https://eudat.eu/communities/an-eudat-based-fair-data-approach-for-data-interoperability) . Within CLARIN, initiatives such as the Language Resource Switchboard and openly go towards methodologies and "systems" to address the interoperability issues. From a technical point of view the main issues are briefly reported below: 1. Many tools in OpeNer and PANACEA are command line ones; 2. OpeNer o_ers both POST and GET API; 3. PANACEA built its Web Services using Soaplab11 and o_ers SOAP Web Services; 4. KAF, LMF and GrAF guarantee the interoperability among data and services; 5. Simple pipelines are available in OpeNer, while a workow engine has been used in PANACEA. Tools are already wrapped, but to fully meet the requirements of both LRS and WebLicht we have to build a new shell around the command line tools so that REST APIs can accept both POST and GET requests and accept/produce different formats. Indeed if Language Resource Switchboard accepts tools with their output format but requires to read data from URL in plain text, WebLicht accepts tools which read and write the TCF format. While OpeNer requires that the core (the command line) be wrapped into a REST shell, Web Services in PANACEA need REST APIs around a SOAP core. In the final paper, we will finalize the technical aspects and describe how the User Involvement group can play an important role in poking the sentiment/opinion community in CLARIN.}, KEYWORDS = {Web Services, Clarin, Research Infrastructures}, URL = {https://indico.egi.eu/indico/event/3455/contribution/139}, CONFERENCE_NAME = {Digital Infrastructures for Research 2017}, CONFERENCE_PLACE = {Brussels, The Square Meeting Centre}, CONFERENCE_DATE = {30/11/2017, 1/12/2017}, } @INPROCEEDINGS{NICOLAS_2017_INPROCEEDINGS_NKMDCAEBQ_375984, AUTHOR = {Nicolas, L. and Konig, A. and Monachini, M. and Del Gratta, R. and Calamai, S. and Abel, A. and Enea, A. and Biliotti, F. and Quochi, V.}, TITLE = {CLARIN-IT: State of Affairs, Challenges and Opportunities}, YEAR = {2017}, ABSTRACT = {This paper provides an overview on the Italian national CLARIN consortium and the status of CLARIN-IT in general. It thus discusses the current state of affairs of the consortium and provi-des information on the members, especially with regards to what they offer to CLARIN in terms of resources, services and expertise, and what CLARIN offers them to further their own research.}, KEYWORDS = {Italian CLARIN consortium, CLARIN-IT}, PAGES = {4}, URL = {https://www.clarin.eu/event/2017/clarin-annual-conference-2017-budapest-hungary}, CONFERENCE_NAME = {CLARIN Annual Conference 2017}, CONFERENCE_PLACE = {Budapest, Hungary}, CONFERENCE_DATE = {18-20 September, 2017}, } @INPROCEEDINGS{PARDELLI_2017_INPROCEEDINGS_PGBD_366597, AUTHOR = {Pardelli, G. and Giannini, S. and Boschetti, F. and Del Gratta, R.}, TITLE = {AIUCD e CLiC-it: citazioni bibliografiche a confronto}, YEAR = {2017}, ABSTRACT = {Il lavoro propone l'analisi e il confronto dei riferimenti bibliografici delle cinque edizioni annuali della Conferenza dell'Associazione per l'Informatica Umanistica e la Cultura Digitale (AIUCD) e del primo biennio (2014-2015) della Conferenza Italiana di Linguistica Computazionale (CLiC-it) per misurare la direzione in cui si muove il trend citazionale.. L'analisi muove dal principio di rilevanza della citazione nella trasmissione della conoscenza in un periodo di grandi cambiamenti socioculturali e di importanti evoluzioni nelle modalità di produzione e diffusione dei risultati della ricerca scientifica. Lo scopo dello studio è quello di misurare la gamma delle risorse citate in questa area del sapere mediante l'uso di indicatori volti a comprendere la loro ampiezza, l'estensione temporale, la varietà, le relazioni con il mondo editoriale e i modelli di riferimento. L'osservazione dei risultati consente di classificare i documenti citati, di descriverne le caratteristiche e di valutare eventuali trasformazioni rispetto alle modalità di citazione tradizionali. -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- The paper suggests the analysis of the bibliographic references - enclosed in the proceedings of the Italian Conference on Computational Linguistics - CLICit in 2014-2015 biennium and of five AIUCD Conference editions 2012-2016 . The analysis moves from the principle of relevance of citation in the transmission of knowledge in a period of great socio-cultural changes and important developments in the production and dissemination of the results in the scientific research. The purpose of the study is to measure the range of resources cited in this area of knowledge by the use of indicators aimed in understanding their wideness, the time extension, the variety, the relations with the publishing world and the reference models. The observation of the results allows to classify the cited document, to describe its characteristics and to assess any changes compared to the traditional citation mode.}, KEYWORDS = {Corpus bibliografico, Analisi di metadati}, PAGES = {38-50}, URL = {http://aiucd2017.aiucd.it/wp-content/uploads/2017/01/book-of-abstract-AIUCD-2017.pdf}, CONFERENCE_NAME = {AIUCD 2017 Conference \& 3rd EADH Day}, CONFERENCE_PLACE = {Roma, Università "Sapienza"}, CONFERENCE_DATE = {24-28 January 2017}, BOOKTITLE = {AIUCD 2017 Conference}, } @ARTICLE{MUGELLI_2016_ARTICLE_MBDDKT_364960, AUTHOR = {Mugelli, G. and Boschetti, F. and Del Gratta, R. and Del Grosso, A. M. and Khan, F. and Taddei, A.}, TITLE = {A user-centred design to annotate ritual facts in ancient greek tragedies}, YEAR = {2016}, ABSTRACT = {Euporia is an annotation system developed with a user-centred approach for the study of ritual and religion in ancient Greek tragedy. Euporia adopts a domain specific language (DSL) and a lightweight web user interface in order to offer digital support to an anthropological study of ancient Greek tragedy that compares ritual as it is performed or described in Greek tragedy with ancient ritual as it can be reconstructed from literary, archaeological, and epigraphic sources. The case study discussed in this paper (Aesch. Ag 67-71) shows one of the main features of Euporia: the ability to annotate different readings and different interpretations of the text and their consequences in the reconstruction of ancient Greek ritual.}, KEYWORDS = {Digital Philology, Digital Humanities, Digital Classicist, Computational philology, Computational Linguistics}, PAGES = {103-120}, URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-85007489227\&origin=inward}, VOLUME = {59}, DOI = {10.1111/j.2041-5370.2016.12041.x}, PUBLISHER = {Institute of Classical Studies, University of London (London, Regno Unito)}, ISSN = {0076-0730}, JOURNAL = {Bulletin-University of London. Institute of Classical Studies}, } @INCOLLECTION{DELGRATTA_2016_INCOLLECTION_DBDKM_353799, AUTHOR = {Del Gratta, R. and Boschetti, F. and Del Grosso, A. and Khan, F. and Monachini, M.}, TITLE = {Cooperative philology on the way to web services: The case of the cophiwordnet platform}, YEAR = {2016}, ABSTRACT = {In this paper we present ongoing research carried out at the Institute for Computational Linguistics "A. Zampolli" (ILC) in Pisa. The institute has been active since many years in the field of Digital Humanities providing resources, tools and solutions to address issues of the to digital humanists. Starting from those previous initiatives, we show how to re-engineer them as Web Services in order to make connections between lexicons, semantic resources and a fine grained text management. Linked Open Data is chosen as the paradigm used to link the different resources as well as the modality of data presentation.}, KEYWORDS = {Canonical text services, Cooperative philology, Linked open data, Web services}, PAGES = {173-187}, URL = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84961744725\&partnerID=q2rCbXpz}, VOLUME = {9442}, DOI = {10.1007/978-3-319-31468-6_13}, PUBLISHER = {Springer International Publishing (Switzerland, CHE)}, ISBN = {978-3-319-31468-6}, BOOKTITLE = {Worldwide Language Service Infrastructure: Second International Workshop, WLSI 2015, Kyoto, Japan, January 22-23, 2015. Revised Selected Papers}, EDITOR = {Murakami, Y. and Li, D.}, } @INCOLLECTION{FRONTINI_2016_INCOLLECTION_FDM_357638, AUTHOR = {Frontini, F. and Del Gratta, R. and Monachini, M.}, TITLE = {GeoDomainWordNet: Linking the Geonames Ontology to WordNet}, YEAR = {2016}, ABSTRACT = {This paper illustrates the transformation of GeoNames' ontology concepts, with their English labels and glosses, into a GeoDomain WordNet-like resource in English, its translation into Italian, and its linking to the existing generic WordNets of both languages. The paper describes the criteria used for the linking of domain synsets to each other and to the generic ones and presents the published resource in RDF according to the w3c and lemon schema.}, KEYWORDS = {GeoNames, WordNet, Language resources, Lexicons, Linguistic linked data, lemon, RDF}, PAGES = {229-242}, URL = {http://link.springer.com/chapter/10.1007/978-3-319-43808-5_18}, VOLUME = {9561}, DOI = {10.1007/978-3-319-43808-5}, ISBN = {978-3-319-43808-5}, BOOKTITLE = {Human Language Technology. Challenges for Computer Science and Linguistics}, EDITOR = {Vetulani, Z. and Uszkoreit, H. and Kubis, M.}, } @INPROCEEDINGS{BERTI_2016_INPROCEEDINGS_BCYBBD_363704, AUTHOR = {Berti, M. and Crane, G. and Yousef, T. and Bizzoni, Y. and Boschetti, F. and Del Gratta, R.}, TITLE = {Ancient Greek WordNet meets the Dynamic Lexicon: the example of the fragments of the Greek Historians}, YEAR = {2016}, ABSTRACT = {The Ancient Greek WordNet (AGWN) and the Dynamic Lexicon (DL) are multilingual resources to study the lexicon of Ancient Greek texts and their translations. Both AGWN and DL are works in progress that need accuracy improvement and manual validation. After a detailed description of the current state of each work, this paper illustrates a methodology to cross AGWN and DL data, in order to mutually score the items of each resource according to the evidence provided by the other resource. The training data is based on the corpus of the Digital Fragmenta Historicorum Graecorum (DFHG), which includes ancient Greek texts with Latin translations.}, KEYWORDS = {wordnet}, PAGES = {34-38}, URL = {http://gwc2016.racai.ro/procedings.pdf}, ISBN = {978-606-714-239-6}, CONFERENCE_NAME = {Global WordNet Conference}, CONFERENCE_PLACE = {Bucarest}, CONFERENCE_DATE = {27-30/01/2016}, } @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{STANZIONE_2016_INPROCEEDINGS_SRMTBD_363706, AUTHOR = {Stanzione, A. and Re, G. and Mugelli, G. and Taddei, A. and Boschetti, F. and Del Gratta, R.}, TITLE = {Homeric Greek WordNet: costruire una risorsa lessico-semantica fra ricerca e didattica}, YEAR = {2016}, KEYWORDS = {wordnet, semantica, greco antico}, PAGES = {129-132}, URL = {http://www.himeros.eu/aiucd2016/c40.pdf}, CONFERENCE_NAME = {Quinto Convegno Annuale AIUCD. Edizioni digitali: rappresentazione, interoperabilità, analisi del testo e infrastrutture}, CONFERENCE_PLACE = {Ca' Dolfin, Venezia, Italia}, CONFERENCE_DATE = {7-9/9/2016}, BOOKTITLE = {AIUCD 2016-Book of Abstracts}, EDITOR = {Boschetti, F.}, } @ARTICLE{DELGRATTA_2015_ARTICLE_DFKM_287051, AUTHOR = {Del Gratta, R. and Frontini, F. and Khan, F. and Monachini, M.}, TITLE = {Converting the PAROLE SIMPLE CLIPS Lexicon into RDF with lemon}, YEAR = {2015}, ABSTRACT = {This paper describes the publication and linking of (parts of) PAROLE SIMPLE CLIPS (PSC), a large scale Italian lexicon, to the Semantic Web and the Linked Data cloud using the lemon model. The main challenge of the conversion is discussed, namely the reconciliation between the PSC semantic structure which contains richly encoded semantic information, following the qualia structure of the Generative Lexicon theory and the lemon view of lexical sense as a reified pairing of a lexical item and a concept in an ontology. The result is two datasets: one consists of a list of lemon lexical entries with their lexical properties, relations and senses; the other consists of a list of OWL individuals representing the referents for the lexical senses. These OWL individuals are linked to each other by a set of semantic relations and mapped onto the SIMPLE OWL ontology of higher level semantic types.}, KEYWORDS = {lemon, linked data, generative lexicon, RDF, OWL, lexical resource}, PAGES = {387-392}, URL = {http://www.semantic-web-journal.net/content/converting-parole-simple-clips-lexicon-rdf-lemon-0}, VOLUME = {6}, DOI = {10.3233/SW-140168}, PUBLISHER = {IOS Press (Amsterdam, Paesi Bassi)}, ISSN = {1570-0844}, JOURNAL = {Semantic web (Print)}, } @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.}, } @INPROCEEDINGS{PIRRELLI_2015_INPROCEEDINGS_PNBDM_333414, AUTHOR = {Pirrelli, V. and Nahli, O. and Boschetti, F. and Del Gratta, R. and Marzi, C.}, TITLE = {Computational Linguistics and Language Physiology: Insights from Arabic NLP and Cooperative Editing}, YEAR = {2015}, ABSTRACT = {Computer processing of written Arabic raises a number of challenges to traditional parsing architectures on many levels of linguistic analysis. In this contribution, we review some of these core issues and the demands they make, to suggest different strategies to successfully tackle them. In the end, we assess these issues in connection with the behaviour of neuro-biologically inspired lexical architectures known as Temporal Self-Organising Maps. We show that, far from being language-specific problems, issues in Arabic processing can shed light on some fundamental characteristics of the human language processor, such as structure-based lexical recoding, concurrent, competitive activation of output candidates and dynamic selection of optimal solutions.}, KEYWORDS = {Non-concatenative morphology, Optical Character Recognition, WordNet, Temporal Self-organising Maps, Mental Lexicon, Language neuro-physiology}, PAGES = {1-8}, URL = {http://dl.acm.org/citation.cfm?id=2802612}, DOI = {10.1145/2802612.2802637}, ISBN = {978-1-4503-3295-8}, CONFERENCE_NAME = {Third AIUCD Annual Conference-Humanities and Their Methods in the Digital Ecosystem}, CONFERENCE_PLACE = {Bologna (IT)}, CONFERENCE_DATE = {18-19/09/2014}, BOOKTITLE = {Third AIUCD Annual Conference-Humanities and Their Methods in the Digital Ecosystem}, EDITOR = {Tomasi, F. and Del Turco, R. R. and Tammaro, A. M.}, } @INPROCEEDINGS{BOSCHETTI_2015_INPROCEEDINGS_BDDMDN_295474, AUTHOR = {Boschetti, F. and Del Gratta, R. and Del Grosso, A. and Monachini, M. and Diakoff, H. and Nahli, O.}, TITLE = {Collaborative Philology on the way to Web Services: the case of CoPhiWordnet}, YEAR = {2015}, ABSTRACT = {Starting from previous initiatives of the CoPhiLab, we show how they can be reinterpreted as Web Services, especially when they become part of a wider scenario: Web Services are used to make connections between lexicons, semantic resources and a fine grained text management. Linked Open Data is chosen to be the paradigm used to link the dierent resources, but also as the modality of data presentation.}, KEYWORDS = {Collaborative Philology, Web Services, Linked Open Data, Text Services, Text Interpretation}, URL = {http://langrid.org/wlsi2015/program.html}, CONFERENCE_NAME = {The Second International Workshop on Worldwide Language Service Infrastructure, WLSI 2015}, CONFERENCE_PLACE = {Kyoto}, CONFERENCE_DATE = {22-23rd January 2015}, } @INPROCEEDINGS{BIZZONI_2014_INPROCEEDINGS_BBDDMC_286958, AUTHOR = {Bizzoni, Y. and Boschetti, F. and Diakoff, H. and Del Gratta, R. and Monachini, M. and Crane, G.}, TITLE = {The Making of Ancient Greek WordNet}, YEAR = {2014}, ABSTRACT = {This paper describes the process of creation and review of a new lexico-semantic resource for the classical studies: AncientGreekWord- Net. The candidate sets of synonyms (synsets) are extracted from Greek-English dictionaries, on the assumption that Greek words translated by the same English word or phrase have a high probability of being synonyms or at least semantically closely related. The process of validation and the web interface developed to edit and query the resource are described in detail. The lexical coverage of Ancient Greek WordNet is illustrated and the accuracy is evaluated. Finally, scenarios for exploiting the resource are discussed.}, KEYWORDS = {Ancient Greek, Multilingualism, Classical Philology}, PAGES = {1140-1147}, URL = {http://www.lrec-conf.org/proceedings/lrec2014/index.html}, PUBLISHER = {European language resources association (ELRA) (Paris, FRA)}, CONFERENCE_NAME = {LREC 2014. European Language Resources Association ELRA: Paris (Francia)}, 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.}, } @INPROCEEDINGS{BOSCHETTI_2014_INPROCEEDINGS_BDL_288070, AUTHOR = {Boschetti, F. and Del Gratta, R. and Lamé, M.}, TITLE = {Computer Assisted Annotation of Themes and Motifs in Ancient Greek Epigrams: First Steps}, YEAR = {2014}, ABSTRACT = {This paper aims at illustrating some tools to assist the manual annotation of themes and motifs in literary and epigraphic epigrams for the PRIN 2010/2011 Memorata Poetis Project.}, KEYWORDS = {Filologia collaborativa}, PAGES = {83-86}, URL = {http://clic.humnet.unipi.it/it/atti.html}, VOLUME = {1}, DOI = {10.12871/CLICIT2014158}, PUBLISHER = {Pisa University Press (Pisa, ITA)}, ISBN = {978-8-86741-472-7}, CONFERENCE_NAME = {First Italian Conference on Computational Linguistics}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {9-11 dicembre 2014}, BOOKTITLE = {The First Italian Conference on Computational Linguistics-Proceedings}, EDITOR = {Basili, R. and Lenci, A. and Magnini, B.}, } @INPROCEEDINGS{DELGRATTA_2014_INPROCEEDINGS_DFKMS_285395, AUTHOR = {Del Gratta, R. and Frontini, F. and Khan, F. and Mariani, J. and Soria, C.}, TITLE = {The LREMap for Under-Resourced Languages}, YEAR = {2014}, ABSTRACT = {A complete picture of currently available language resources and technologies for the under-resourced languages of Europe is still lacking. Yet this would help policy makers, researchers and developers enormously in planning a roadmap for providing all languages with the necessary instruments to act as fully equipped languages in the digital era. In this paper we introduce the LRE Map and show its utility for documenting available language resources and technologies for under-resourced languages. The importance of the serialization of the LREMap into (L)LOD along with the possibility of its connection to a wider world is also introduced.}, KEYWORDS = {language resources, less-resourced languages, linguistic linked open data}, PAGES = {78-83}, URL = {http://www.lrec-conf.org/proceedings/lrec2014/index.html}, CONFERENCE_NAME = {Workshop on Collaboration and Computing for Under-Resourced Languages in the Linked Open Data Era (CCURL 2014)}, CONFERENCE_PLACE = {Reykjavik}, CONFERENCE_DATE = {26/05/2014}, BOOKTITLE = {Proceedings of the Workshop on Collaboration and Computing for Under-Resourced Languages in the Linked Open Data Era (CCURL 2014)}, EDITOR = {Pretorius, L. and Soria, C. and Baroni, P.}, } @INPROCEEDINGS{DELGRATTA_2014_INPROCEEDINGS_DN_318313, AUTHOR = {Del Gratta, R. and Nahli, O.}, TITLE = {Enhancing Arabic WordNet with the use on Princeton WordNet and a bilingual dictionary}, YEAR = {2014}, ABSTRACT = {This paper describes an heuristic-based approach to enhance existing WordNets with freely available bilingual resources. The approach has been applied to the Arabic WordNet using the AraMorph bilingual dictionary as bilingual resource, but its guidelines are quite general to be effectively applied to other languages. The English words extracted from the bilingual resource are checked against Princeton WordNet in order to quantify their coverage and to select only those words which share the same set of synsets. This strongly reduces the number of Arabic words of the pairs. These latter are then checked against the Arabic WordNet to make new words emerge and -possibly- add new synonyms.}, KEYWORDS = {WordNet, Arabic, English, Bilingual Resource, Enhancement}, PAGES = {278-284}, URL = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=7016632}, DOI = {10.1109/CIST.2014.7016632}, PUBLISHER = {IEEE Communications Society (Piscataway, USA)}, ISBN = {978-1-4799-5978-5}, CONFERENCE_NAME = {ANLP IEEE CIST14}, CONFERENCE_PLACE = {Tetuan, Morocco}, CONFERENCE_DATE = {20-22/10/ 2014}, BOOKTITLE = {3rd International IEEE Colloquium on Information Science and Technology; From 20th to 22nd of October 2014 Tetuan-Chefchaouen Morocco}, } @INPROCEEDINGS{DELGRATTA_2014_INPROCEEDINGS_DPS_281039, AUTHOR = {Del Gratta, R. and Pardelli, G. and Sara, G.}, TITLE = {The LRE Map disclosed}, YEAR = {2014}, ABSTRACT = {This paper describes a serialization of the LRE Map database according to the RDF model. Due to the peculiar nature of the LRE Map, many ontologies are necessary to model the map in RDF, including newly created and reused ontologies. The importance of having the LRE Map in RDF and its connections to other open resources is also addressed.}, KEYWORDS = {Language Resource, LOD, Metadata}, PAGES = {3534-3541}, URL = {http://www.lrec-conf.org/proceedings/lrec2014/index.html}, PUBLISHER = {EUROPEAN LANGUAGE RESOURCES ASSOC-ELRA FRANCE (Parigi, FRA)}, ISBN = {978-2-9517408-8-4}, CONFERENCE_NAME = {Ninth International Conference on Language Resources and Evaluation (LREC'14)}, CONFERENCE_PLACE = {Reykjavik, Iceland}, CONFERENCE_DATE = {26-31 may 2014}, BOOKTITLE = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}, 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{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{BOSCHETTI_2014_INPROCEEDINGS_BDMNP_288372, AUTHOR = {Boschetti, F. and Del Gratta, R. and Marzi, C. and Nahli, O. and Pirrelli, V.}, TITLE = {Modelli, metodi e strumenti per il trattamento automatico della lingua araba e per l'editing in ambienti collaborativi}, YEAR = {2014}, ABSTRACT = {La linguistica computazionale ha portato negli ultimi vent'anni a un profondo mutamento nello studio delle lingue e delle loro testimonianze scritte, spostando l'accento della ricerca da aspetti linguistico-formali all'uso linguistico in contesti comunicativi reali. Il presente contributo illustra l'impatto di questo cambio di prospettiva sullo studio della lingua araba, attraverso una rassegna di alcune attività di ricerca in corso presso l'Istituto di Linguistica Computazionale del CNR di Pisa: I. acquisizione dei testi arabi tramite Optical Character Recognition (OCR) e sviluppo di strumenti per la correzione manuale del testo in ambienti collaborativi; II. sviluppo di algoritmi e strumenti per l'analisi morfologica della lingua araba; III. analisi delle dinamiche di acquisizione del lessico arabo mediante architetture bio-computazionali; IV. sviluppo della WordNet dell'Arabo collegata a Princeton WordNet, ItalWordNet, LatinWordNet e alla nascente AncientGreek WordNet. Queste attivit( sono rivolte sia all'analisi delle caratteristiche linguistiche dell'arabo che allo studio della produzione letteraria araba e dei suoi rapporti storico-culturali con altre lingue. In particolare, il contributo intende illustrare la fertilità di un approccio metodologico che metta in relazione le dinamiche di acquisizione del lessico arabo, con la messa a punto di procedure di analisi ed edizione critica del testo e con i principi di organizzazione ontologica di una lingua ad alta produttività derivazionale.}, URL = {http://aiucd2014.unibo.it/book-of-abstracts.pdf}, CONFERENCE_NAME = {AIUCD 3rd annual conference}, CONFERENCE_PLACE = {Bologna}, CONFERENCE_DATE = {18-19 settembre 2014}, BOOKTITLE = {La metodologia della ricerca umanistica nell'ecosistema digitale-AIUCD 2014 Terzo convegno annuale}, EDITOR = {Rossi, F. and Tomasi, F.}, } @INPROCEEDINGS{FRONTINI_2013_INPROCEEDINGS_FDM_287280, AUTHOR = {Frontini, F. and Del Gratta, R. and Monachini, M.}, TITLE = {Linking the Geonames ontology to WordNet}, YEAR = {2013}, ABSTRACT = {This paper illustrates the transformation of the GeoNames ontology concepts, with their English labels and glosses, into a GeoDomain WordNet-like resource in English, its translation into Italian, and its linking to the existing generic WordNets of both languages.}, KEYWORDS = {GeoNames, WordNet, lemon}, PAGES = {263-267}, URL = {http://hnk.ffzg.hr/bibl/ltc2013/book/papers/OWN-2.pdf}, PUBLISHER = {Fundacja Uniwersytetu im A. Mickiewicza (Poznan, POL)}, ISBN = {978-2-9517408-8-4}, CONFERENCE_NAME = {6th Language \& Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics}, CONFERENCE_PLACE = {Poznan, Poland}, CONFERENCE_DATE = {December 7-9, 2013}, BOOKTITLE = {Human Language Technologies as a Challenge for Computer Science and Linguistics. Proceedings, 6th Language \& Technology Conference, December 7-9, 2013, Poznañ, Poland}, EDITOR = {Vetulani, Z. 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_DFMQRAL_223098, AUTHOR = {Del Gratta, R. and Frontini, F. and Monachini, M. and Quochi, V. and Rubino, F. and Abrate, M. and Lo Duca, A.}, TITLE = {L-LEME: an Automatic Lexical Merger based on the LMF Standard}, YEAR = {2012}, ABSTRACT = {The present paper describes LMF LExical MErger (L-LEME), an architecture to combine two lexicons in order to obtain new resource(s). L-LEME relies on standards, thus exploiting the benefits of the ISO Lexical Markup Framework (LMF) to ensure interoperability. L-LEME is meant to be dynamic and heavily adaptable: it allows the users to configure it to meet their specific needs. The L-LEME architecture is composed of two main modules: the Mapper, which takes in input two lexicons A and B and a set of user-defined rules and instructions to guide the mapping process (Directives D) and gives in output all matching entries. The algorithm also calculates a cosine similarity score. The Builder takes in input the previous results, a set of Directives D1 and produces a new LMF lexicon C. The Directives allow the user to define its own building rules and different merging scenarios. L-LEME is applied to a specific concrete task within the PANACEA project, namely the merging of two Italian SubCategorization Frame (SCF) lexicons. The experiment is interesting in that A and B have different philosophies behind, being A built by human introspection and B automatically extracted. Ultimately, L-LEME has interesting repercussions in many language technology applications}, KEYWORDS = {LMF, Lexicon mapping, similarity score}, PAGES = {31-40}, URL = {https://publications.cnr.it/doc/223098}, ISBN = {978-2-9517408-7-7}, CONFERENCE_NAME = {The Eight International Conference on Language Resources and Evaluation (LREC) 2012}, CONFERENCE_PLACE = {Istanbul, Turkey}, CONFERENCE_DATE = {2012}, BOOKTITLE = {Proceedings of the LREC 2012 Workshop on Language Resource Merging}, EDITOR = {Bel, N. and Gavrilidou, M. and Monachini, M. and Quochi, V. and Rimell, L.}, } @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}, } @TECHREPORT{DELGRATTA_2012_TECHREPORT_DMTALRBP_484488, AUTHOR = {Del Gratta, R. and Monachini, M. and Tesconi, M. and Abrate, M. and Lo Duca, A. and Rimell, L. and Bel, N. and Padró, M.}, TITLE = {D6. 4 Lexical Merger}, YEAR = {2012}, ABSTRACT = {This document describes the experiments on the merging of lexical resources performed during the project and the development of two merging components for LMF lexicons}, KEYWORDS = {LFM, Lexical Merger}, PAGES = {1-39}, URL = {http://www.panacea-lr.eu/system/deliverables/PANACEA_D6.4.pdf}, } @TECHREPORT{POCH_2012_TECHREPORT_PHQDTTPB_221573, AUTHOR = {Poch, M. and Hamon, O. and Quochi, V. and Del Gratta, R. and Toral, A. and Thurmair, G. and Prokopidis, P. and Bel, N.}, TITLE = {D3. 4 Third version (v4) of the integrated platform and documentation}, YEAR = {2012}, ABSTRACT = {The deliverable describes the third and final version of the PANACEA platform.}, KEYWORDS = {infrastrutture Trattamento del linguaggio naturale}, URL = {https://publications.cnr.it/doc/221573}, } @TECHREPORT{RIMELL_2012_TECHREPORT_RBPFMQD_221650, AUTHOR = {Rimell, L. and Bel, N. and Padró, M. and Frontini, F. and Monachini, M. and Quochi, V. and Del Gratta, R.}, TITLE = {D6. 5 Merged dictionaries}, YEAR = {2012}, ABSTRACT = {This document presents the merged dictionaries delivered in PANACEA. Those dictionaries result from merging already existing lexica, generally for general domain, with domain specific lexica acquired using PANACEA platform. The domain specific lexica are presented and delivered in D6.3 and the merging repository that allowed the multilevel merging in D6.4.}, KEYWORDS = {merged dictionaries, computational lexicon}, URL = {http://www.panacea-lr.eu//en/deliverables/list}, } @TECHREPORT{RIMELL_2012_TECHREPORT_RBPFMQD_221755, AUTHOR = {Rimell, L. and Bel, N. and Padrò, M. and Frontini, F. and Monachini, M. and Quochi, V. and Del Gratta, R.}, TITLE = {D6. 3 Monolingual lexica for English, Spanish and Italian tuned for a particular domain (LAB and ENV)}, YEAR = {2012}, ABSTRACT = {This document presents the lexica acquired using PANACEA platform for Labour and Environment domains. The languages of the lexica are English, Spanish and Italian. The lexical information acquired depends on the language, according to the available tools in the platform.}, KEYWORDS = {Lexicon Acqusition}, URL = {http://www.panacea-lr.eu/system/deliverables/PANACEA_D6.3.pdf}, } @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}, } @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}, } @TECHREPORT{ARRANZ_2011_TECHREPORT_ABBCCDFGMQRR_290606, AUTHOR = {Arranz, V. and Bel, N. and Budin, G. and Caselli, T. and Choukri, K. and Del Gratta, R. and Frontini, F. and Goggi, S. and Monachini, M. and Quochi, V. and Rubino, F. and Russo, I.}, TITLE = {The FLaReNet Databook}, YEAR = {2011}, ABSTRACT = {The FLaReNet Databook is not only the collection of all the factual material collected during the activities of the project, but also a set on innovative initiatives and instruments that will remain in place for the continuous collection of such "facts". The purpose of the Databook is in fact, on one side, to consolidate the analyses carried out in the project and, at the same time, to set up the proper mechanisms that will enable the provision of a continuous stream of relevant factual material, also after the end of the project.}, KEYWORDS = {Language Resources (LRs)}, PAGES = {1-8}, URL = {http://www.flarenet.eu/?q=FLaReNet_Databook}, } @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}, } @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{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{HAWAYEK_2010_INPROCEEDINGS_HDC_84797, AUTHOR = {Hawayek, A. and Del Gratta, R. and Cappelli, G.}, TITLE = {A bilingual dictionary Mexican Sign Language-Spanish/Spanish-Mexican Sign Language}, YEAR = {2010}, ABSTRACT = {We present a three-part bilingual specialized dictionary Mexican Sign Language-Spanish / Spanish-Mexican Sign Language. This dictionary will be the outcome of a three-years agreement between the Italian "Consiglio Nazionale delle Ricerche" and the Mexican Conacyt. Although many other sign language dictionaries have been provided to deaf communities, there are no Mexican Sign Language dictionaries in Mexico, yet. We want to stress on the specialized feature of the proposed dictionary: the bilingual dictionary will contain frequently used general Spanish forms along with scholastic course specific specialized words whose meanings warrant comprehension of school curricula. We emphasize that this aspect of the bilingual dictionary can have a deep social impact, since we will furnish to deaf people the possibility to get competence in official language, which is necessary to ensure access to school curriculum and to become full-fledged citizens. From a technical point of view, the dictionary consists of a relational database, where we have saved the sign parameters and a graphical user interface especially designed to allow deaf children to retrieve signs using the relevant parameters and,thus, the meaning of the sign in Spanish.}, KEYWORDS = {Sign Language Recognition/Generation, Lexicon, Lexical database, Acquisition}, PAGES = {3055-3062}, URL = {http://www.lrec-conf.org/proceedings/lrec2010/index.html}, ISBN = {2-9517408-6-7}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {17-23/05/2010}, } @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}, } @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{DELGRATTA_2008_INPROCEEDINGS_DRT_84728, AUTHOR = {Del Gratta, R. and Ruimy, N. and Toral, A.}, TITLE = {Simple-Clips ongoing research: more information with less data by implementing inheritance}, YEAR = {2008}, ABSTRACT = {This paper presents the application of inheritance to the formal taxonomy (is-a) of a semantically rich Lexical Resource (LR) based on the Generative Lexicon theory, SIMPLE-CLIPS. The aim is to lighten the representation of its semantic layer by reducing the number of encoded relations. A prediction calculation on the impact of introducing inheritance as regards space occupancy is carried out, which yields a significant space reduction of 22%. This is corroborated by its actual application that reduces the number of explicitly encoded relations in this lexicon by 18.4%. Later on, we study the issues that inheritance poses to the Lexical Resources and discuss sensitive solutions, illustrated by examples, to tackle each of them. Finally, we present a discussion on the application of inheritance, from which two advantages arise: consistency enhancement and inference capabilities.}, KEYWORDS = {Lexicon, Knowledge representation, Lexical database}, PAGES = {2380-2385}, URL = {https://publications.cnr.it/doc/84728}, ISBN = {2-9517408-4-0}, CONFERENCE_NAME = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Marrakech, Marocco}, CONFERENCE_DATE = {28-30/5/2008}, } @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{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{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}, } @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{DELGRATTA_2007_TECHREPORT_DBCEMQS_157442, AUTHOR = {Del Gratta, R. and Bartolini, R. and Caselli, T. and Enea, A. and Monachini, M. and Quochi, V. and Sassolini, V.}, TITLE = {TimeML: An Ontological Mapping onto the UIMA Type Systems}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157442}, } @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{DELGRATTA_2007_TECHREPORT_DTQM_157441, AUTHOR = {Del Gratta, R. and Toral, A. and Quochi, V. and Monachini, M.}, TITLE = {LocalBioLex: A database framework for biolinguistic research on integrated databases}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157441}, } @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}, }