@INPROCEEDINGS{ALZETTA_2018_INPROCEEDINGS_ADMSV_391617, AUTHOR = {Alzetta, C. and Dell'Orletta, F. and Montemagni, S. and Simi, M. and Venturi, G.}, TITLE = {Assessing the Impact of Iterative Error Detection and Correction. A Case Study on the Italian Universal Dependency Treebank}, YEAR = {2018}, ABSTRACT = {Detection and correction of errors and inconsistencies in "gold treebanks" are becoming more and more central topics of corpus annotation. The paper illustrates a new incremental method for enhancing treebanks, with particular emphasis on the extension of error patterns across different textual genres and registers. Impact and role of corrections have been assessed in a dependency parsing experiment carried out with four different parsers, whose results are promising. For both evaluation datasets, the performance of parsers increases, in terms of the standard LAS and UAS measures and of a more focused measure taking into account only relations involved in error patterns, and at the level of individual dependencies.}, KEYWORDS = {Error Detection, Universal Dependency Treebanks, Syntactic parsing}, PAGES = {1-7}, URL = {http://universaldependencies.org/udw18/PDFs/39_Paper.pdf}, ISBN = {978-1-948087-84-1}, CONFERENCE_NAME = {Universal Dependencies Workshop 2018 (UDW 2018)}, CONFERENCE_PLACE = {Brussels}, CONFERENCE_DATE = {01/11/2018}, } @ARTICLE{ATTARDI_2015_ARTICLE_ABBCDMPSS_366713, AUTHOR = {Attardi, G. and Basile, V. and Bosco, C. and Caselli, T. and Dell'Orletta, F. and Montemagni, S. and Patti, V. and Simi, M. and Sprugnoli, R.}, TITLE = {State of the Art Language Technologies for Italian: The EVALITA 2014 Perspective}, YEAR = {2015}, ABSTRACT = {Shared task evaluation campaigns represent a well established form of competitive evaluation, an important opportunity to propose and tackle new challenges for a specific research area and a way to foster the development of benchmarks, tools and resources. The advantages of this approach are evident in any experimental field, including the area of Natural Language Processing. An outlook on state-of-the-art language technologies for Italian can be obtained by reflecting on the results of the recently held workshop "Evaluation of NLP and Speech Tools for Italian", EVALITA 2014. The motivations underlying individual shared tasks, the level of knowledge and development achieved within each of them, the impact on applications, society and economy at large as well as directions for future research will be discussed from this perspective.}, KEYWORDS = {Evaluation Campaign, Natural Language Processing, Dependency Parsing, Sentiment Analysis, Temporal Processing}, PAGES = {43-61}, URL = {https://publications.cnr.it/doc/366713}, VOLUME = {9}, DOI = {10.3233/IA-150076}, PUBLISHER = {Associazione Italiana per l'Intelligenza Artificiale (Bari, Italia)}, ISSN = {1724-8035}, JOURNAL = {Intelligenza Artificiale}, } @INCOLLECTION{SIMI_2015_INCOLLECTION_SMB_330110, AUTHOR = {Simi, M. and Montemagni, S. and Bosco, C.}, TITLE = {Harmonizing and merging Italian treebanks: Towards a merged Italian dependency treebank and beyond}, YEAR = {2015}, ABSTRACT = {In this paper we address the challenge of combining existing CoNLL-compliant dependency-annotated corpora with the final aim of constructing a bigger treebank for the Italian language. To this end, we defined amethodology formapping different annotation schemes, based on: (i)The analysis of similarities and differences of considered source and target dependency annotation schemes; (ii) The analysis of the performance of state of the art dependency parsers trained on the source and target treebanks; (iii) The mapping of the source annotation scheme(s) onto a set of target (possibly underspecified) data categories. This methodology was applied in two different case studies. The first one was aimed at constructing a "Merged Italian Dependency Treebank" (MIDT) starting from existing Italian dependency treebanks, namely TUT and ISST-TANL. The second case study, still ongoing, consists in the conversion of the MIDT resource into the Stanford Dependencies de facto standard with the final aim of developing an "Italian Stanford Dependency Treebank" (ISDT).}, KEYWORDS = {Harmonization and merging of resources, Italian, Dependency Treebank}, PAGES = {3-23}, URL = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84927143016\&partnerID=q2rCbXpz}, VOLUME = {589}, DOI = {10.1007/978-3-319-14206-7_1}, PUBLISHER = {Springer International Publishing (CH-6330 Cham (ZG), CHE)}, ISBN = {978-3-319-14205-0}, BOOKTITLE = {Harmonization and Development of Resources and Tools for Italian Natural Language Processing within the PARLI Project}, EDITOR = {Basili, R. and Bosco, C. and Delmonte, R. and Moschitti, A. and Simi, M.}, } @EDITORIAL{BOSCO_2014_EDITORIAL_BCDFMS_330112, AUTHOR = {Bosco, C. and Cosi, P. and Dell'Orletta, F. and Falcone, M. and Montemagni, S. and Simi, M.}, TITLE = {Proceedings of the Fourth International Workshop EVALITA 2014}, YEAR = {2014}, KEYWORDS = {Trattamento Automatico del Linguaggio, Speech Processing, Lingua Italiana}, PAGES = {167}, URL = {http://clic.humnet.unipi.it/proceedings/Proceedings-EVALITA-2014.pdf}, PUBLISHER = {Pisa University Press (Pisa, ITA)}, ISBN = {978-88-67414-72-7}, } @INPROCEEDINGS{SIMI_2014_INPROCEEDINGS_SBM_329779, AUTHOR = {Simi, M. and Bosco, C. and Montemagni, S.}, TITLE = {Less is More? Towards a Reduced Inventory of Categories for Training a Parser for the Italian Stanford Dependencies}, YEAR = {2014}, ABSTRACT = {Stanford Dependencies (SD) represent nowadays a de facto standard as far as dependency annotation is concerned. The goal of this paper is to explore pros and cons of different strategies for generating SD annotated Italian texts to enrich the existing Italian Stanford Dependency Treebank (ISDT). This is done by comparing the performance of a statistical parser (DeSR) trained on a simpler resource (the augmented version of the Merged Italian Dependency Treebank or MIDT+) and whose output was automatically converted to SD, with the results of the parser directly trained on ISDT. Experiments carried out to test reliability and effectiveness of the two strategies show that the performance of a parser trained on the reduced dependencies repertoire, whose output can be easily converted to SD, is slightly higher than the performance of a parser directly trained on ISDT. A non-negligible advantage of the first strategy for generating SD annotated texts is that semi-automatic extensions of the training resource are more easily and consistently carried out with respect to a reduced dependency tagset. Preliminary experiments carried out for generating the collapsed and propagated SD representation are also reported.}, KEYWORDS = {Italian Treebank, Harmonization and Merging of Resources, Stanford Dependencie s}, URL = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/818_Paper.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, 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{BOSCO_2013_INPROCEEDINGS_BMS_329780, AUTHOR = {Bosco, C. and Montemagni, S. and Simi, M.}, TITLE = {Converting Italian Treebanks: Towards an Italian Stanford Dependency Treebank}, YEAR = {2013}, ABSTRACT = {The paper addresses the challenge of converting MIDT, an existing dependency-based Italian treebank resulting from the harmonization and merging of smaller resources, into the Stanford Dependencies annotation formalism, with the final aim of constructing a standard-compliant resource for the Italian language. Achieved results include a methodology for converting treebank annotations belonging to the same dependency-based family, the Italian Stanford Dependency Treebank (ISDT), and an Italian localization of the Stanford Dependency scheme.}, KEYWORDS = {Italian Treebank, Harmonization and Merging of Resources, Stanford Dependencie s}, PAGES = {61-69}, URL = {http://aclweb.org/anthology/W13-2308}, ISBN = {978-1-937284-58-9}, CONFERENCE_NAME = {7th Linguistic Annotation Workshop and Interoperability with Discourse}, CONFERENCE_PLACE = {Sofia, Bulgaria}, CONFERENCE_DATE = {8-9 August 2013}, BOOKTITLE = {Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse}, } @INPROCEEDINGS{BOSCO_2012_INPROCEEDINGS_BMS_330109, AUTHOR = {Bosco, C. and Montemagni, S. and Simi, M.}, TITLE = {Harmonization and Merging of two Italian Dependency Treebanks}, YEAR = {2012}, ABSTRACT = {The paper describes the methodology which is currently being defined for the construction of a "Merged Italian Dependency Treebank" (MIDT) starting from already existing resources. In particular, it reports the results of a case study carried out on two available dependency treebanks, i.e. TUT and ISST-TANL. The issues raised during the comparison of the annotation schemes underlying the two treebanks are discussed and investigated with a particular emphasis on the definition of a set of linguistic categories to be used as a "bridge" between the specific schemes. As an encoding format, the CoNLL de facto standard is used.}, KEYWORDS = {Syntactic Annotation, Merging of Resources, Dependency Parsing}, PAGES = {23-30}, URL = {http://www.lrec-conf.org/proceedings/lrec2012/workshops/06.LREC%202012%20Merging%20Proceedings.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {978-2-9517408-7-7}, CONFERENCE_NAME = {LREC 2012 Workshop on Language Resource Merging}, CONFERENCE_PLACE = {Istambul}, CONFERENCE_DATE = {22 May 2012}, BOOKTITLE = {Proceedings of the LREC 2012 Workshop on Language Resource Merging}, EDITOR = {Bel, N.}, } @INPROCEEDINGS{ATTARDI_2010_INPROCEEDINGS_ADDLMS_84775, AUTHOR = {Attardi, G. and Dei Rossi, S. and Di Pietro, G. and Lenci, A. and Montemagni, S. and Simi, M.}, TITLE = {A Resource and Tool for Super-sense Tagging of Italian Texts}, YEAR = {2010}, KEYWORDS = {Corpus (creation, annotation, etc.), Tools, Systems, Applications, Statistical and machine learning methods}, URL = {https://publications.cnr.it/doc/84775}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {2010}, } @INPROCEEDINGS{BOSCO_2010_INPROCEEDINGS_BMMLDLLASLHNN_84789, AUTHOR = {Bosco, C. and Montemagni, S. and Mazzei, A. and Lombardo, V. and Dell'Orletta, F. and Lenci, A. and Lesmo, L. and Attardi, G. and Simi, M. and Lavelli, A. and Hall, J. and Nilsson, J. and Nivre, J.}, TITLE = {Comparing the Influence of Different Treebank Annotations on Dependency Parsing}, YEAR = {2010}, KEYWORDS = {Parsing, Corpus (creation, annotation, etc.), Evaluation methodologies}, URL = {https://publications.cnr.it/doc/84789}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {2010}, } @INPROCEEDINGS{ATTARDI_2009_INPROCEEDINGS_ADSDV_84761, AUTHOR = {Attardi, G. and Dell'Orletta, F. and Simi, M. and Dei Rossi, S. and Vecchi, E. M.}, TITLE = {The Tanl Named Entity Recognizer at Evalita 2009}, YEAR = {2009}, KEYWORDS = {Named Entity Recognizer}, URL = {https://publications.cnr.it/doc/84761}, CONFERENCE_NAME = {Evaluation of NLP and Speech Tools for Italian 2009}, CONFERENCE_PLACE = {Reggio Emilia, Italy}, } @INPROCEEDINGS{ATTARDI_2009_INPROCEEDINGS_ADST_84734, AUTHOR = {Attardi, G. and Dell'Orletta, F. and Simi, M. and Turian, J.}, TITLE = {Accurate Dependency Parsing with a Stacked Multilayer Perceptron}, YEAR = {2009}, KEYWORDS = {Dependency Parsing, Parsing, Multilayer Perceptron}, URL = {https://publications.cnr.it/doc/84734}, CONFERENCE_NAME = {Evaluation of NLP and Speech Tools for Italian 2009}, CONFERENCE_PLACE = {Reggio Emilia, Italy}, } @TECHREPORT{MONTEMAGNI_2007_TECHREPORT_MS_157420, AUTHOR = {Montemagni, S. and Simi, M.}, TITLE = {The Italian dependency annotated corpus developed for the CoNLL-2007 Shared Task}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157420}, } @ARTICLE{BERTAGNA_2005_ARTICLE_BCS_30871, AUTHOR = {Bertagna, F. and Chiran, L. and Simi, M.}, TITLE = {ILC-UniPi Italian QA}, YEAR = {2005}, ABSTRACT = {This paper introduces the general architecture of a prototype for monolingual Italian QA. The adopted strategies, the tools and resources for the linguistic processing are presented, together with the system results. We would like to thank Simone Pecunia and Giuseppe Attardi for their indispensable help and Nicoletta Calzolari and Irina Prodanof for their comments and suggestions. We also thank Roberto Bartolini, Alessandro Lenci, Simonetta Montemagni and Vito Pirrelli for the kind concession of text analysis tools.}, PAGES = {569-580}, URL = {https://publications.cnr.it/doc/30871}, VOLUME = {3491}, PUBLISHER = {Springer (Berlin, Germania)}, ISSN = {0302-9743}, JOURNAL = {Lecture notes in computer science}, } @INPROCEEDINGS{BERTAGNA_2004_INPROCEEDINGS_BCS_84603, AUTHOR = {Bertagna, F. and Chiran, L. and Simi, M.}, TITLE = {QA at ILC-UniPI: Description of the Prototype}, YEAR = {2004}, URL = {https://publications.cnr.it/doc/84603}, CONFERENCE_NAME = {CLEF 2004 Workshop}, CONFERENCE_PLACE = {Bath, UK}, CONFERENCE_DATE = {2004}, }