@INPROCEEDINGS{SCIOLETTE_2023_INPROCEEDINGS_SMG_491771, AUTHOR = {Sciolette, F. and Marchi, S. and Giovannetti, E.}, TITLE = {Towards a New Computational Lexicon for Italian: building the morphological layer by harmonizing and merging existing resources}, YEAR = {2023}, ABSTRACT = {The present work illustrates the first steps towards the construction of a new computational lexicon for the Italian language. Following an analysis of existing lexical resources, it was decided to use LexicO as the reference base. In this first phase a resource of nearly 800,000 inflected forms was produced, accompanied by lemmas and morphological traits, obtained by integrating the available data in LexicO with those coming from two support sources: the tool MAGIC and a selection of Italian treebanks.}, KEYWORDS = {computational lexicon, lexical resources, morphology, morphological harmonization}, PAGES = {5}, URL = {https://ceur-ws.org/Vol-3596/short20.pdf}, VOLUME = {3596}, CONFERENCE_NAME = {9th Italian Conference on Computational Linguistics}, CONFERENCE_PLACE = {Venezia}, CONFERENCE_DATE = {30/11/2023-01/12/2023}, BOOKTITLE = {Proceedings of the 9th Italian Conference on Computational Linguistics}, EDITOR = {Boschetti, F. and Lebani, G. E. and Magnini, B. and Novielli, N.}, } @TECHREPORT{ALBANESI_2023_TECHREPORT_AGMPS_491776, AUTHOR = {Albanesi, D. and Giovannetti, E. and Marchi, S. and Papini, M. and Sciolette, F.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-Rapporto tecnico 23}, YEAR = {2023}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto del Progetto Traduzione Talmud Babilonese nel periodo gennaio 2023 - giugno 2023. Le principali attività tecniche svolte sul sistema Traduco attualmente in produzione sono state la risoluzione di bug e l'aggiornamento di alcune funzionalità. Parallelamente, è proseguito il lavoro di ricerca e sviluppo su due fronti: i) la realizzazione della nuova versione di Traduco, ii) l'ampliamento della risorsa lessicale per l'italiano contemporaneo a supporto della funzionalità di ricerca full-text sul testo del Talmud tradotto in italiano.}, KEYWORDS = {Lessici elettronici, rappresentazione della conoscenza, Linguistica Computazionale, traduzione di testi religiosi, traduzione assistita dal calcolatore}, PAGES = {13}, URL = {https://publications.cnr.it/doc/491776}, } @MISC{GIOVANNETTI_2023_MISC_GABCGMPS_491773, AUTHOR = {Giovannetti, E. and Albanesi, D. and Bellandi, A. and Carniani, E. and Guidi, L. and Marchi, S. and Papini, M. and Sciolette, F.}, TITLE = {Maia}, YEAR = {2023}, ABSTRACT = {Maia is an open and collaborative web tool based on semantic web and linked open data technologies for text annotation, e-lexicography, and lexical linking.}, KEYWORDS = {maia, linked open data, e-lexicography, text annotation, lexical linking, collaborative tools}, URL = {https://github.com/klab-ilc-cnr/Maia}, } @ARTICLE{SAPONARO_2022_ARTICLE_SGS_484519, AUTHOR = {Saponaro, D. and Giovannetti, E. and Sciolette, F.}, TITLE = {From Religious Sources to Computational Resources: Approach and Case Study on Hebrew Terms and Concepts}, YEAR = {2022}, ABSTRACT = {This paper introduces a methodology for the creation of a digital representation of a religious case study integrating textual, linguistic, and conceptual entities. the description of a holistic model of text, to be used as the backbone of the computational resource that needs to be built, is provided. the proposed case study, focusing on the semantic field of "face" in Jewish religion, is first introduced from the point of view of the scholar and then translated, with the support of digital tools, into the relative computational representation}, KEYWORDS = {religious studies, Hebrew terminology, ontology}, PAGES = {21}, URL = {https://publications.cnr.it/doc/484519}, VOLUME = {XXVII(2022)}, PUBLISHER = {Giuntina (Firenze, Italia)}, ISSN = {2282-4499}, JOURNAL = {Materia giudaica Print}, } @INCOLLECTION{SCIOLETTE_2022_INCOLLECTION_SG_470011, AUTHOR = {Sciolette, F. and Giovannetti, E.}, TITLE = {Un modello per domarli tutti: verso una rappresentazione del testo come esplicitazione di documento, lingua e contenuto}, YEAR = {2022}, ABSTRACT = {The aim of this research is to describe the first steps towards the theoretical elaboration of a holistic model to represent textual information. The focus of the model is the definition of "text", with its different dimensions, as a "diasystem". The set of elements, organized into distinct but strictly interconnected systems, wherein each element has an effect on the whole diasystem, is described in a model structured in the following components: graphic, linguistic, documental, discursive, and conceptual. In this work, the first attempts in the modeling of text will be shown through two case studies: the Babylonian Talmud and the DiTMAO (Dictionary of Old Occitan medico-botanical terminology).}, KEYWORDS = {textual model, holystic model, diasystem, model of text}, PAGES = {145-157}, URL = {http://www.aitla.it/images/pdf/StudiAItLA14/009_AItLA14_ScioletteGiovannetti.pdf}, VOLUME = {14}, PUBLISHER = {Officinaventuno (Milano, ITA)}, ISBN = {978-88-97657-51-4}, BOOKTITLE = {Fare linguistica applicata con le digital humanities}, EDITOR = {Saturno, J. and Spreafico, L.}, } @INPROCEEDINGS{COLOMBO_2022_INPROCEEDINGS_CG_463100, AUTHOR = {Colombo, M. and Giovannetti, E.}, TITLE = {La Visualizzazione Grafica di Sensi e Relazioni Semantiche di un Lessico Computazionale della Lingua Italiana}, YEAR = {2022}, ABSTRACT = {La visualizzazione, intesa come ausilio alla consultazione e alla ricerca, può giocare un ruolo fondamentale nella fruizione di dati linguistici e di conoscenza. Attraverso la rappresentazione di una risorsa lessicale o di una ontologia sotto forma di grafo, ad esempio, uno studioso ha la possibilità di farsi un'idea immediata delle relazioni che intercorrono tra i vari elementi di un lessico (di lingua o specialistico) o dei concetti che formalizzano un determinato dominio. In questo contributo presentiamo un'applicazione web based per la visualizzazione grafica della componente semantica di un lessico computazionale dell'italiano. Il grafo è stato sviluppato con Cytoscape.js, una libreria Javascript per la creazione di grafi. L'interfaccia al grafo, sviluppata come applicazione Angular, offre un primo insieme di funzionalità di interazione per la navigazione e la manipolazione della risorsa lessico-semantica.}, KEYWORDS = {human-computer interaction, lessico computazionale, grafi, Visualizzazione grafica di risorse linguistiche, rappresentazione della conoscenza}, PAGES = {155-160}, URL = {http://amsacta.unibo.it/6848/1/Proceedings_AIUCD2022.pdf}, DOI = {10.6092/unibo/amsacta/6848}, ISBN = {9788894253566}, CONFERENCE_NAME = {AIUCD 2022}, CONFERENCE_PLACE = {Lecce}, CONFERENCE_DATE = {1-3/06/2022}, BOOKTITLE = {AIUCD 2022-Culture digitali. Intersezioni: filosofia, arti, media. Proceedings della 11a conferenza nazionale}, } @INPROCEEDINGS{MARCHI_2022_INPROCEEDINGS_MCDG_463120, AUTHOR = {Marchi, S. and Colombo, M. and Dattilo, D. and Giovannetti, E.}, TITLE = {Un esperimento di visualizzazione grafica della terminologia del Talmud babilonese}, YEAR = {2022}, ABSTRACT = {L'impiego di tecnologie di information visualization nel settore delle digital humanities può aprire nuove frontiere di ricerca. Le informazioni veicolate attraverso modalità grafiche, infatti, possono apparire agli studiosi più immediatamente comprensibili e le interfacce grafiche realizzate fornire inediti paradigmi di studio e di manipolazione dei dati analizzati. Il caso d'uso sperimentale illustrato in questo contributo è stato concepito per fornire allo studioso una modalità visiva, immediata, per l'analisi comparativa del contenuto terminologico di un corpus testuale.}, KEYWORDS = {Visualizzazione grafica di risorse testuali, terminologia, linguistica computazionale, tf-idf, grafi}, PAGES = {239-241}, URL = {http://amsacta.unibo.it/6848/1/Proceedings_AIUCD2022.pdf}, DOI = {10.6092/unibo/amsacta/6848}, ISBN = {9788894253566}, CONFERENCE_NAME = {AIUCD 2022}, CONFERENCE_PLACE = {Lecce}, CONFERENCE_DATE = {1-3/06/2022}, BOOKTITLE = {AIUCD 2022-Culture digitali. Intersezioni: filosofia, arti, media. Proceedings della 11a conferenza nazionale}, } @TECHREPORT{ALBANESI_2022_TECHREPORT_ABCGMPS_470012, AUTHOR = {Albanesi, D. and Bellandi, A. and Colombo, M. and Giovannetti, E. and Marchi, S. and Papini, M. and Sciolette, F.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-Rapporto tecnico 21}, YEAR = {2022}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto del Progetto Traduzione Talmud Babilonese nel periodo novembre 2021 - aprile 2022. Le principali attività tecniche svolte sul sistema Traduco sono state la risoluzione di bug e l'implementazione di nuove funzionalità richieste. Parallelamente, è stata realizzata una applicazione per la consultazione del corpus biblico e sono proseguite le attività volte alla visualizzazione di risorse lessicali tramite grafi e per l'analisi, l'allineamento di testi, l'aggiornamento e la conversione del lessico computazionale PSC da utilizzarsi per la consultazione avanzata, su base morfologica e semantica, del testo talmudico tradotto in italiano.}, KEYWORDS = {Traduzione Assistita dal Calcolatore, Traduzione Collaborativa, Lessici elettronici, rappresentazione della conoscenza, Linguistica Computazionale, traduzione di testi religiosi}, PAGES = {23}, URL = {https://publications.cnr.it/doc/470012}, } @TECHREPORT{ALBANESI_2022_TECHREPORT_ACGMPS_475381, AUTHOR = {Albanesi, D. and Colombo, M. and Giovannetti, E. and Marchi, S. and Papini, M. and Sciolette, F.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-Rapporto tecnico 22}, YEAR = {2022}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto del Progetto Traduzione Talmud Babilonese nel periodo maggio 2022 - dicembre 2022. Le principali attività tecniche svolte sul sistema Traduco sono state la risoluzione di bug e l'implementazione di nuove funzionalità richieste. Parallelamente, è proseguito il lavoro di ricerca e sviluppo su tre fronti: i) la nuova versione di Traduco, ii) la visualizzazione grafica di risorse lessicali, e iii) la ricerca full-text sul testo del Talmud tradotto in italiano.}, KEYWORDS = {Traduzione Assistita dal CalcolatoreTraduzione Collaborativa, Lessici elettronici, rappresentazione della conoscenza, Linguistica Computazionale, traduzione di testi religiosi, ricerca full-text}, PAGES = {40}, URL = {https://publications.cnr.it/doc/475381}, } @TECHREPORT{ALBANESI_2022_TECHREPORT_AGP_470013, AUTHOR = {Albanesi, D. and Giovannetti, E. and Papini, M.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-rapporto integrativo 4}, YEAR = {2022}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto delle attività di progetto previste dalla convenzione integrativa stipulata tra PTTB e ILC-CNR in data 10/07/2018 e condotte nel periodo febbraio 2021 - gennaio 2022.}, KEYWORDS = {Linguistica Computazionale, Traduzione di Testi Religiosi, Traduzione Assistita dal Calcolatore, Traduzione Collaborativa, Sviluppo front-end}, PAGES = {15}, URL = {https://publications.cnr.it/doc/470013}, } @ARTICLE{GIOVANNETTI_2021_ARTICLE_GABDDM_457778, AUTHOR = {Giovannetti, E. and Albanesi, D. and Bellandi, A. and Dattilo, D. and Del Grosso, A. M. and Marchi, S.}, TITLE = {An ontology of masters of the Babylonian Talmud}, YEAR = {2021}, ABSTRACT = {The purpose of this research is to build an ontology of the masters appearing in the Babylonian Talmud (BT). The ontology built so far has been shared as a Linked Open Data and it will be linked to existing vocabularies. This work has been developed in the context of the Babylonian Talmud Translation Project, where more than eighty Talmudists are working together, since 2012, at the translation (comprehensive of explicative notes and glossaries) of the Talmud into Italian. The construction of the resource has involved the application of tools leveraging on computational linguistics approaches. The ontology, already describing more than 500 masters, constitutes the first portion of a more comprehensive Talmudic Knowledge Base where the text itself, the terminology, the entities, and the concepts constituting the BT will be formalized and linked to each other.}, KEYWORDS = {ontology, babylonian talmud, terminology, word alignment, linked open data, semantic web, knowledge representation}, PAGES = {725-737}, URL = {https://academic.oup.com/dsh/article-abstract/37/3/725/6410110}, VOLUME = {37}, DOI = {10.1093/llc/fqab043}, PUBLISHER = {Oxford University Press (Oxford, UK, Regno Unito)}, ISSN = {2055-7671}, JOURNAL = {Digital Scholarship in the Humanities}, } @INPROCEEDINGS{GIOVANNETTI_2021_INPROCEEDINGS_GABMPS_463795, AUTHOR = {Giovannetti, E. and Albanesi, D. and Bellandi, A. and Marchi, S. and Papini, M. and Sciolette, F.}, TITLE = {The role of a computational lexicon for query expansion in full-text search}, YEAR = {2021}, ABSTRACT = {This work describes the first experiments conducted with a computational lexicon of Italian in a context of query expansion for full-text search. An application, composed of a graphical user interface and backend services to access the lexicon and the database containing the corpus to be queried, was developed. The text was morphologically analysed to improve the precision of the search process. Some examples of queries are given to show the potential of a text search approach supported by a complex and stratified lexical resource.}, KEYWORDS = {full-text search, computational lexicon, query expansion}, PAGES = {162-168}, URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-85121247840\&origin=inward}, VOLUME = {3033}, DOI = {10.4000/books.aaccademia.10417}, PUBLISHER = {Accademia University Press (Torino, ITA)}, ISSN = {1613-0073}, ISBN = {9791280136947}, CONFERENCE_NAME = {CLiC-it 2021 Italian Conference on Computational Linguistics 2021}, CONFERENCE_PLACE = {Milan, Italy}, CONFERENCE_DATE = {January 26-28, 2022}, BOOKTITLE = {Proceedings of the Eight Italian Conference on Computational Linguistics (Clic-it 2021)}, EDITOR = {Fersini, E. and Passarotti, M. and Patti, V.}, } @TECHREPORT{ALBANESI_2021_TECHREPORT_ABCPGS_463868, AUTHOR = {Albanesi, D. and Bellandi, A. and Colombo, M. and Papini, M. and Giovannetti, E. and Sciolette, F.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-Rapporto tecnico 19}, YEAR = {2021}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto del Progetto Traduzione Talmud Babilonese nel periodo novembre 2020 - aprile 2021. Le principali attività tecniche svolte sul sistema Traduco sono state la risoluzione di bug, l'implementazione di nuove funzionalità richieste e lo sviluppo di una nuova interfaccia grafica utente. Le attività di ricerca sono state condotte, in continuità a quelle descritte nel rapporto precedente, nella rappresentazione del lessico, della terminologia e della conoscenza del Talmud.}, KEYWORDS = {Linguistica Computazionale, Traduzione di Testi Religiosi, Traduzione Assistita dal Calcolatore, Traduzione Collaborativa, Lessici elettronici, rappresentazione della conoscenza}, PAGES = {28}, URL = {https://publications.cnr.it/doc/463868}, } @TECHREPORT{ALBANESI_2021_TECHREPORT_ABCPGS_463870, AUTHOR = {Albanesi, D. and Bellandi, A. and Colombo, M. and Papini, M. and Giovannetti, E. and Sciolette, F.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-Rapporto tecnico 20}, YEAR = {2021}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto del Progetto Traduzione Talmud Babilonese nel periodo maggio 2021 - ottobre 2021. Le principali attività tecniche svolte sul sistema Traduco sono state la risoluzione di bug e l'implementazione di nuove funzionalità richieste. Parallelamente, sono proseguite le attività volte alla visualizzazione di risorse testuali e linguistiche tramite grafi e per la conversione e l'utilizzo del lessico computazionale PSC a supporto di ricerca "full-text" sul testo talmudico italiano.}, KEYWORDS = {Traduzione Assistita dal Calcolatore, Traduzione Collaborativa, Lessici elettronici, rappresentazione della conoscenza, Linguistica Computazionale, traduzione di testi religiosi}, PAGES = {20}, URL = {https://publications.cnr.it/doc/463870}, } @TECHREPORT{ALBANESI_2021_TECHREPORT_AGPS_463871, AUTHOR = {Albanesi, D. and Giovannetti, E. and Papini, M. and Sciolette, F.}, TITLE = {Traduco: l'Applicazione Web Linguistico-Computazionale per il Progetto di Traduzione del Talmud Babilonese-rapporto integrativo 3}, YEAR = {2021}, ABSTRACT = {La presente relazione tecnico-scientifica descrive l'attività svolta da ILC-CNR nel contesto delle attività di progetto previste dalla convenzione integrativa stipulata tra PTTB e ILC-CNR in data 10/07/2018 e condotte nel periodo febbraio 2020 - gennaio 2021.}, KEYWORDS = {Linguistica Computazionale, Traduzione di Testi Religiosi, Traduzione Assistita dal Calcolatore, Traduzione Collaborativa, Sviluppo front-end, lessici computazionali}, PAGES = {17}, URL = {https://publications.cnr.it/doc/463871}, } @ARTICLE{GIOVANNETTI_2020_ARTICLE_GBDDMPP_453583, AUTHOR = {Giovannetti, E. and Bellandi, A. and Dattilo, D. and Del Grosso, A. M. and Marchi, S. and Pecchioli, A. and Piccini, S.}, TITLE = {The Terminology of the Babylonian Talmud: Extraction, Representation and Use in the Context of Computational Linguistics}, YEAR = {2020}, ABSTRACT = {A formal digital structuring of the terminology of the Talmud is being carried out in the context of the Project for the Translation of the Babylonian Talmud in Italian. The terminological resource was encoded in the form of a multi-language Explanatory Combinatorial Dictionary (Hebrew-Aramaic-Italian) according to the principles of the Meaning-Text Theory. The construction of such a resource was supported by text processing and computational linguistics techniques aimed at automatically extracting terms from the Italian translation of the Talmud and aligning them with the corresponding Hebrew/Aramaic source terms. The paper describes the process that was set up for the construction of the terminological resource with the ultimate goal of illustrating the advantages of the adoption of a formal linguistic model. The terminological resource aims, indeed, to be a useful tool to deepen the characteristics of the languages of the Talmud, to help translators in their work and more generally scholars in their study of the Talmud itself.}, KEYWORDS = {Babylonian Talmud, Computational Linguistics, Explanatory and Combinatorial Lexicology}, PAGES = {61-74}, URL = {https://publications.cnr.it/doc/453583}, VOLUME = {XXV}, DOI = {10.1400/283235}, PUBLISHER = {Giuntina (Firenze, Italia)}, ISSN = {2282-4499}, JOURNAL = {Materia giudaica Print}, } @INPROCEEDINGS{BELLANDI_2020_INPROCEEDINGS_BG_427282, AUTHOR = {Bellandi, A. and Giovannetti, E.}, TITLE = {Involving Lexicographers in the LLOD Cloud with LexO, an Easy-to-use Editor of Lemon Lexical Resources}, YEAR = {2020}, ABSTRACT = {In this contribution, we show LexO, a user-friendly web collaborative editor of lexical resources based on the lemon model. LexO has been developed in the context of Digital Humanities projects, in which a key point in the design of an editor was the ease of use by lexicographers with no skill in Linked Data or Semantic Web technologies. Though the tool already allows creating a lemon lexicon from scratch and lets a team of users work on it collaboratively, many developments are possible. The involvement of the LLOD community appears now crucial both to find new users and application fields where to test it, and, even more importantly, to understand in which way it should evolve.}, KEYWORDS = {lexO, lexical resources editor, semantic web, llod}, PAGES = {70-74}, URL = {https://www.aclweb.org/anthology/2020.ldl-1.10.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, ISBN = {979-10-95546-36-8}, CONFERENCE_NAME = {7th Workshop on Linked Data in Linguistics (LDL-2020)}, CONFERENCE_PLACE = {Marseille, France}, CONFERENCE_DATE = {22-23/06/2020}, EDITOR = {Ionov, M. and McCrae, J. P. and Chiarcos, C. and Declerck, T. and Bosque Gil, J. and Gracia, J.}, } @INPROCEEDINGS{DELGROSSO_2020_INPROCEEDINGS_DGM_427281, AUTHOR = {Del Grosso, A. M. and Giovannetti, E. and Marchi, S.}, TITLE = {Enriching a Multilingual Terminology Exploiting Parallel Texts: An Experiment on the Italian Translation of the Babylonian Talmud}, YEAR = {2020}, ABSTRACT = {Parallel texts can represent an extremely useful source of information in a number of text and linguistic processing tasks. In this work we show an experiment conducted on the Italian translation of the Babylonian Talmud, a text we have analyzed and processed to support in the construction of a multilingual Hebrew/Aramaic/Italian terminological resource. The approach we adopted comprised: i) the TEI encoding of the text, ii) the automatic extraction of the Italian terms, iii) the addition of Hebrew/Aramaic terms via word-by-word alignment, iv) the revision of the obtained results.}, KEYWORDS = {multilingual terminology, parallel text, text alignment, babylonian talmud}, PAGES = {119-124}, URL = {http://amsacta.unibo.it/6316/1/AIUCD_2020_volume_FINAL.pdf}, DOI = {10.6092/unibo/amsacta/6316}, ISBN = {978-88-942535-4-2}, CONFERENCE_NAME = {IX Convegno Annuale AIUCD}, CONFERENCE_PLACE = {Milano: Università Cattolica del Sacro Cuore}, CONFERENCE_DATE = {15-17/01/2020}, } @ARTICLE{DELGROSSO_2019_ARTICLE_DCCDGMSS_427276, AUTHOR = {Del Grosso, A. M. and Capizzi, E. and Cristofaro, S. and De Luca, M. R. and Giovannetti, E. and Marchi, S. and Seminara, G. and Spampinato, D.}, TITLE = {Bellini's Correspondence: a Digital Scholarly Edition for a Multimedia Museum}, YEAR = {2019}, ABSTRACT = {Within the "Museo Virtuale della Musica BellinInRete" project, a corpus of letters, written by the renowned composer Vincenzo Bellini (1801-1835) from Catania, will be encoded and made publicly available. This contribution aims at illustrating the part of the project regarding the implementation of the prototype for the metadata and text encoding, indexing and visualisation of Bellini's correspondence. The encoding scheme has been defined according to the latest guidelines of the Text Encoding Initiative and it has been instantiated on a sample of letters. Contextually, a first environment has been implemented by customizing two open source tools: Edition Visualization Technology and Omega Scholarly platform. The main objective of the digital edition is to engage general public with the cultural heritage held by the Belliniano Civic Museum of Catania. This wide access to Bellini's correspondence has been conceived preserving the scholarly transcriptions of the letters edited by Seminara within her most recent critical edition (Olschki, 2017). The digital edition of the corpus takes care of handling the correspondence metadata by means of the correspDesc TEI tagset. Finally, Bellini's letters will be accessible via the Web platform as well as integrated into a forthcoming interactive and multimedia tour hosted at the museum.}, KEYWORDS = {digital scholarly edition, correspondence, Digital and Computational Philology, Software Design, Vincenzo Bellini, Music, Multimedia Museum}, PAGES = {23-47}, URL = {https://umanisticadigitale.unibo.it/article/view/9162/9918}, VOLUME = {7}, DOI = {10.6092/issn.2532-8816/9162}, ISSN = {2532-8816}, JOURNAL = {Umanistica Digitale}, } @INCOLLECTION{GIOVANNETTI_2019_INCOLLECTION_G_457777, AUTHOR = {Giovannetti, E.}, TITLE = {Traduzione Talmud Babilonese}, YEAR = {2019}, ABSTRACT = {Traduzione Talmud Babilonese è un progetto di ricerca che ha come obiettivo la traduzione in lingua italiana del Talmud Babilonese, un testo fondamentale della cultura ebraica non solo in campo religioso ma che tocca anche ogni aspetto della conoscenza umana, dalla giurisprudenza alla scienza, dalla filosofia alla vita di tutti i giorni}, KEYWORDS = {traduzione assistita dal calcolatore, talmud babilonese}, PAGES = {126-126}, URL = {https://publications.cnr.it/doc/457777}, VOLUME = {1}, DOI = {10.36173/PLURIMI-2019-1}, PUBLISHER = {CNR EDIZIONI (ROMA, ITA)}, ISBN = {9788880803775}, BOOKTITLE = {Linguaggi, ricerca, comunicazione. Focus CNR}, EDITOR = {Cadeddu, M. E. and Marras, C.}, } @ARTICLE{PECCHIOLI_2018_ARTICLE_PABGM_397525, AUTHOR = {Pecchioli, A. and Albanesi, D. and Bellandi, A. and Giovannetti, E. and Marchi, S.}, TITLE = {Annotazione Linguistica Automatica dell'Ebraico Mishnaico: Esperimenti sul Talmud Babilonese}, YEAR = {2018}, ABSTRACT = {The automatic linguistic analysis of ancient Hebrew represents a new research opportunity in the field of Jewish studies. In fact, very little has been produced, both in terms of linguistic resources and, above all, of tools for the analysis of ancient Hebrew. This article illustrates a work born within the Italian Translation of the Babylonian Talmud Project aimed at the construction of an automatic linguistic annotator of Mishnaic Hebrew.}, KEYWORDS = {Babylonian Talmud, Natural Language Processing, Mishnaic Hebrew}, PAGES = {281-291}, URL = {http://aisg.cise.unipi.it/Materia-giudaica-2018/018-Pecchioli%20pp%20281-292B.pdf}, VOLUME = {XXIII}, PUBLISHER = {Giuntina (Firenze, Italia)}, ISSN = {2282-4499}, JOURNAL = {Materia giudaica Print}, } @INPROCEEDINGS{DELGROSSO_2018_INPROCEEDINGS_DBGMN_390296, AUTHOR = {Del Grosso, A. M. and Bellandi, A. and Giovannetti, E. and Marchi, S. and Nahli, O.}, TITLE = {Scanning is Just the Beginning: Exploiting Text and Language Technologies to Enhance the Value of Historical Manuscripts}, YEAR = {2018}, ABSTRACT = {In this paper we present a digital process for the explicitation of the textual, linguistic and semantic content of historical manuscripts. The proposed workflow is composed of a sequence of incremental steps, each of which is described both on a methodological and practical perspective. The steps are: 1) visualization and structuring of metadata, 2) transcription, 3) structural encoding, 4) annotation, 5) lexical and conceptual structuring.}, KEYWORDS = {Computational Lexica, Digital Scholarly Editing, Digital Humanities, al-Qamus al-Muhit}, PAGES = {214-219}, URL = {https://publications.cnr.it/doc/390296}, DOI = {10.1109/CIST.2018.8596373}, PUBLISHER = {IEEE (New York, USA)}, ISBN = {978-1-5386-4385-3}, CONFERENCE_NAME = {CIST 2018 WH-MNLP}, CONFERENCE_PLACE = {MARRAKECH, MOROCCO}, CONFERENCE_DATE = {21-27/10/2018}, BOOKTITLE = {Colloquium in Information Science and Technology, CIST}, EDITOR = {Al Achhab, M. and El Mohajir, M. and Jellouli, I. and El Mohajir, B. E.}, } @INPROCEEDINGS{BELLANDI_2018_INPROCEEDINGS_BGP_385403, AUTHOR = {Bellandi, A. and Giovannetti, E. and Piccini, S.}, TITLE = {Collaborative Editing of Lexical and Termino-ontological Resources: a Quick Introduction to LexO}, YEAR = {2018}, ABSTRACT = {We here present LexO, a web collaborative editor of lexical and termino-ontological resources. As the underlying lexical model we adopted lemon, which appeared to be perfect for our purposes, in particular regarding the separation between the conceptual and linguistic dimensions .}, KEYWORDS = {lemon model, lexo, collaborative editor, termino-ontological resource}, PAGES = {23-27}, URL = {http://euralex2018.cjvt.si/wp-content/uploads/sites/6/2018/12/Euralex2018_book_of_abstracts_FINAL.pdf}, CONFERENCE_NAME = {XVIII EURALEX International Congress}, CONFERENCE_PLACE = {Ljubljana, Slovenia}, CONFERENCE_DATE = {17-21/07/2018}, BOOKTITLE = {The XVIII EURALEX International Congress: Lexicography in Global Contexts-Book of Abstracts}, EDITOR = {Čibej, J. and Gorjanc, V. and Kosem, I. and Krek, S.}, } @INPROCEEDINGS{DELGROSSO_2018_INPROCEEDINGS_DCDGMSS_384781, AUTHOR = {Del Grosso, A. M. and Cristofaro, S. and De Luca, M. R. and Giovannetti, E. and Marchi, S. and Seminara, G. and Spampinato, D.}, TITLE = {Le lettere di Bellini: dalla Carta al Web}, YEAR = {2018}, ABSTRACT = {Nel contesto del progetto "Museo virtuale della Musica BellinInRete" sarà reso fruibile, attraverso un processo di acquisizione, codifica e pubblicazione digitale, un corpus di lettere di Vincenzo Bellini, compositore catanese del XIX secolo. L'edizione digitale delle lettere belliniane sarà consultabile in rete e, inoltre, sarà integrata in un percorso museale interattivo in allestimento presso il Museo Civico Belliniano di Catania.}, KEYWORDS = {Digital Edition, Digital Scholarly Platform}, PAGES = {60-64}, URL = {http://www.aiucd2018.uniba.it/content/AIUCD2018-BoA.pdf}, DOI = {10.6092/unibo/amsacta/5997}, ISBN = {9788894253528}, CONFERENCE_NAME = {AIUCD 2018 Conference}, CONFERENCE_PLACE = {Bari}, CONFERENCE_DATE = {31/01/2018-02/02/2018}, BOOKTITLE = {AIUCD 2018-Book of abstracts}, EDITOR = {Spampinato, D.}, } @INPROCEEDINGS{GIOVANNETTI_2018_INPROCEEDINGS_GABDDPP_385407, AUTHOR = {Giovannetti, E. and Albanesi, D. and Bellandi, A. and Dattilo, D. and Dollinar, M. and Pecchioli, A. and Piperno, C.}, TITLE = {Il Progetto Traduzione del Talmud Babilonese: il Ruolo della Tecnologia e della Linguistica Computazionale}, YEAR = {2018}, ABSTRACT = {L'obiettivo principale del Progetto Traduzione del Talmud Babilonese è produrre la traduzione del Talmud in italiano. La traduzione, affidata ad un team di circa 80 studiosi, è condotta con l'aiuto di Traduco, un software preposto ad agevolare tutte le fasi di lavoro previste dal progetto, dall'attribuzione degli utenti alle sezioni da tradurre, fino al supporto all'impaginazione finale. La presenza di una piattaforma collaborativa digitale che già, di per sé, costituisce una innovazione nell'ambito dei grandi progetti di traduzione, è arricchita da algoritmi per il trattamento automatico del testo e della lingua, in costante evoluzione, attraverso i quali il traduttore, il revisore o lo studioso possono contare su funzionalità sempre più avanzate.}, KEYWORDS = {Linguistica Computazionale, Traduzione di Testi Religiosi, Traduzione Assistita dal Calcolatore, Traduzione Collaborativa}, PAGES = {144-146}, URL = {http://amsacta.unibo.it/5997/}, DOI = {10.6092/unibo/amsacta/5997}, ISBN = {9788894253528}, CONFERENCE_NAME = {AIUCD 2018 Conference}, CONFERENCE_PLACE = {Bari}, CONFERENCE_DATE = {31/01/2018-02/02/2018}, BOOKTITLE = {AIUCD 2018-Book of abstracts}, EDITOR = {Spampinato, D.}, } @INPROCEEDINGS{PICCINI_2018_INPROCEEDINGS_PBG_385401, AUTHOR = {Piccini, S. and Bellandi, A. and Giovannetti, E.}, TITLE = {A Semantic Web Approach to Modelling and Building a Bilingual Chinese-Italian Termino-ontological Resource}, YEAR = {2018}, ABSTRACT = {This paper introduces a bilingual Chinese-Italian onto-terminological resource, devoted to modelling the Chinese terminology of Matteo Ricci's World Map (1602), together with the Italian translation by Pasquale D'Elia (1835) [3]. The Map was created in collaboration with the Chinese mathematician and astronomer Li Zizhao, and is entitled ? ? ? ? ? ? Kunyu Wanguo Quantu (literally "Map of the Ten Thousand Countries of the Earth"). Its publication in China was significant as it was the first map to show the Americas, and to represent the world as a sphere. Its large number of cartouches provide information about the geography, history and customs of the world at that time as well as cosmological and cosmographic data. The map had a revolutionary impact from a linguistic standpoint as well: a large number of neologisms were introduced by Ricci, many of which have survived until today.}, KEYWORDS = {termino-ontological resource, classical chinese, lemon model}, PAGES = {87-90}, URL = {http://euralex2018.cjvt.si/wp-content/uploads/sites/6/2018/12/Euralex2018_book_of_abstracts_FINAL.pdf}, CONFERENCE_NAME = {XVIII EURALEX International Congress}, CONFERENCE_PLACE = {Ljubljana, Slovenia}, CONFERENCE_DATE = {17-21/07/2018}, BOOKTITLE = {The XVIII EURALEX International Congress: Lexicography in Global Contexts-Book of Abstracts}, EDITOR = {Čibej, J. and Gorjanc, V. and Kosem, I. and Krek, S.}, } @ARTICLE{GIOVANNETTI_2017_ARTICLE_GABB_364947, AUTHOR = {Giovannetti, E. and Albanesi, D. and Bellandi, A. and Benotto, G.}, TITLE = {Traduco: A collaborative web-based CAT environment for the interpretation and translation of texts}, YEAR = {2017}, ABSTRACT = {Traduco is a web-based collaborative tool aimed at supporting the translation of texts that pose particular challenging interpretative issues. Nowadays, Computer-Assisted Translation (CAT) tools are mainly applied to the translation of technical manuals or legislative texts and are aimed at speeding up the translation process. Traduco extends most of the standard components of a traditional CAT tool with specific features necessary to support the interpretation and translation of complex texts (like the Babylonian Talmud, that we here present as a case study), which pose particular comprehension issues. Traduco goes beyond the translation and its printing: it includes features for the addition of notes and annotations and the creation of glossaries. Translators, editors, supervisors, and end-users accessing Traduco are able to use components that can ease the translation process through the use of CAT technologies, the supervision and managing of the whole process of translation and publishing, the exporting of translations and notes in standard formats for desktop publishing software and TEI format, and, soon, the possibility to perform automatic linguistic analysis of the text. Moreover, Traduco allows the users to insert notes, comments, annotations, and bibliographical references. The design and development of Traduco required the adoption of a multidisciplinary approach, leveraging on advances in software engineering, computational linguistics, knowledge engineering, and publishing.}, KEYWORDS = {computer-assisted translation, talmud, progetto traduzione del talmud babilonese}, PAGES = {47-62}, URL = {http://dsh.oxfordjournals.org/content/early/2016/10/26/llc.fqw054}, VOLUME = {32}, DOI = {10.1093/llc/fqw054}, PUBLISHER = {Oxford University Press (Oxford, UK, Regno Unito)}, ISSN = {2055-7671}, JOURNAL = {Digital Scholarship in the Humanities}, } @INPROCEEDINGS{BELLANDI_2017_INPROCEEDINGS_BGPW_377421, AUTHOR = {Bellandi, A. and Giovannetti, E. and Piccini, S. and Weingart, A.}, TITLE = {Developing LexO: a Collaborative Editor of Multilingual Lexica and Termino-ontological Resources in the Humanities}, YEAR = {2017}, ABSTRACT = {In this paper we present a first version of LexO, a collaborative editor of multilingual lexica and termino-ontological resources. It is based on the lemon model, and aims at supporting lexicographers and terminologists in their work. Although the development of LexO is still ongoing, the editor is already being used within two research projects in the field of Computational Linguistics applied to Humanities: DiTMAO and Totus Mundus. This allowed to test the functionalities of LexO, and prove its high degree of flexibility according to the different extensions of the lemon model needed to fulfill the needs of the involved scholars.}, KEYWORDS = {lexo, multi-lingual termino-ontological resources, DiTMAO, Totus Mundus}, URL = {http://www.aclweb.org/anthology/W17-7000}, CONFERENCE_NAME = {Workshop on Language, Ontology, Terminology and Knowledge Structures-LOTKS 2017}, CONFERENCE_PLACE = {Montpellier}, CONFERENCE_DATE = {19/09/2017}, BOOKTITLE = {Proceedings of Language, Ontology, Terminology and Knowledge Structures Workshop (LOTKS 2017)}, } @INPROCEEDINGS{GIOVANNETTI_2017_INPROCEEDINGS_GABDD_377423, AUTHOR = {Giovannetti, E. and Albanesi, D. and Bellandi, A. and Dattilo, D. and Dell'Orletta, F.}, TITLE = {Stylometry in Computer-Assisted Translation: Experiments on the Babylonian Talmud}, YEAR = {2017}, ABSTRACT = {The purpose of this research is to experiment the application of stylometric techniques in the area of Computer-Assisted Translation to reduce the revision effort in the context of a collaborative, large scale translation project. The obtained results show a correlation between the editing extent and the compliance to some specific linguistic features, proving that supporting translators in writing translations following a desired style can actually reduce the number of following necessary interventions (and, consequently, save time) by revisors, editors and curators.}, KEYWORDS = {traduco, babylonian talmud, computer-assisted translation, stylometry, readability}, PAGES = {177-182}, URL = {https://publications.cnr.it/doc/377423}, PUBLISHER = {Accademia University Press (Torino, ITA)}, ISBN = {9788899982942}, CONFERENCE_NAME = {Fourth Italian Conference on Computational Linguistics (CLiC-it)}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {11-13/12/2017}, BOOKTITLE = {Proceedings of 4th Italian Conference on Computational Linguistics (CLiC-it)}, EDITOR = {Basili, R. and Nissim, M. and Satta, G.}, } @INPROCEEDINGS{DELGROSSO_2017_INPROCEEDINGS_DGM_377409, AUTHOR = {Del Grosso, A. M. and Giovannetti, E. and Marchi, S.}, TITLE = {Il modello a microkernel di Omega nello sviluppo di strumenti per lo studio dei testi: dagli ADT alle API}, YEAR = {2017}, KEYWORDS = {microkernel, studio del testo, Omega, ADT, API}, PAGES = {199-205}, URL = {https://publications.cnr.it/doc/377409}, ISBN = {978-88-942535-1-1}, CONFERENCE_NAME = {AIUCD 2017 Conference}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {24-28/01/2017}, } @INPROCEEDINGS{DELGROSSO_2017_INPROCEEDINGS_DGM_377413, AUTHOR = {Del Grosso, A. M. and Giovannetti, E. and Marchi, S.}, TITLE = {Thinking like the "Modern Operating Systems": The Omega architecture and the Clavius on the Web project}, YEAR = {2017}, ABSTRACT = {The current digital turn in studying and analyzing historical documents results in both having machine actionable cultural data and providing software able to process them. However, these data and services often lack in integration strategies among them in order to be reused in other contexts different from the original ones. As pointed out by Franz Fischer in a worthy of note article: "There is no out-of-the-box software available for creating truly critical and truly digital editions at the same time" [1]. Likewise, Monica Berti stated that is now important to "build a model for representing quotations and text reuses of lost works in a digital environment" [2]. In this vision Bridget Almas is in charge of developing an integrated platform for collaboratively transcribing, editing, and translating historical documents and texts. She claimed that through this platform, called Perseids, students and scholars are able to create open source digital scholarly editions [3]. A number of interesting projects are currently under development to realize general models, digital services, and online tools that can be adopted as part of a long-term infrastructure for managing digital editions. Among Perseids and others, we cite as reference systems (a) the Textual Community project led by P. Robinson and B. Bordalejo, (b) the AustESE project led by the Australian eResearch group, (c) the Tagore Online Variorum "Bichitra" project led by Sukanta Chaudhuri, (d) Homer Multitext led by Neel Smith and Christopher Blackwell, (e) Sharing Ancient Wisdoms founded by the HERA network.}, KEYWORDS = {Omega, object-oriented design, digital scholarly editing, clavius on the web}, URL = {https://publications.cnr.it/doc/377413}, CONFERENCE_NAME = {Global Philology Open Conference}, CONFERENCE_PLACE = {Leipzig}, CONFERENCE_DATE = {20-23/02/2017}, } @INPROCEEDINGS{PICCINI_2017_INPROCEEDINGS_PMG_378393, AUTHOR = {Piccini, S. and Marchi, S. and Giovannetti, E.}, TITLE = {Étudier le structuralisme par le structuralisme: expériences de sémantique distributionnelle dans la construction d'un lexique électronique de la terminologie saussurienne}, YEAR = {2017}, ABSTRACT = {En 2010-2011, le premier lexique électronique dédié à la terminologie linguistique saussurienne a été créé [1] dans le cadre d'un projet de recherche intitulé « Pour une édition numérique des manuscrits de Ferdinand de Saussure », projet coordonné par le Professeur Gambarara. La première étape de construction de la ressource lexicale a consisté en l'identification manuelle dans les textes des termes clés du vocabulaire saussurien et de leurs propriétés sémantiques. L'informatique n'est intervenue que dans la phase de formalisation des données extraites. C'est pourquoi nous nous proposons d'illustrer ici la possibilité de recourir à des techniques automatiques et, en particulier, à des algorithmes de sémantique distributionnelle [2] pour identifier les relations que les termes entretiennent entre eux dans le texte. La méthodologie sous-jacente est basée sur l'hypothèse distributionnelle selon laquelle plus deux mots sont sémantiquement proches, plus ils ont tendance à se produire dans des contextes similaires. Le lexique d'un texte est considéré comme un espace métrique où chaque mot peut être représenté comme un vecteur à n dimensions, chacune d'elles enregistrant le nombre de fois que ce mot apparaît dans un contexte donné. La proximité spatiale entre deux vecteurs indique la similarité sémantique entre deux mots. Elle est calculée par le cosinus de l'angle compris entre les deux vecteurs : plus la valeur du cosinus est grande, plus les termes sont, en principe, sémantiquement similaires. Les techniques computationnelles ont été appliquées aux mêmes textes à partir desquels le lexique électronique a été construit : le Cours de linguistique générale [3], les Écrits de linguistique générale [4] et le Recueil des publications scientifiques [5]. Bien qu'au stade préliminaire, l'expérience a permis d'obtenir des résultats intéressants. À titre d'exemple, nous présentons ci-dessous (Tableau) les valeurs de similitude obtenues par l'algorithme entre le terme signe et d'autres mots dans les textes. Si l'on compare les résultats avec l'entrée du lexique signe, on peut remarquer que l'algorithme est en mesure de détecter un grand nombre de liens explicités dans la ressource et de suggérer, en outre, des relations possibles avec d'autres termes comme valeur, rapport, idée. L'application de ces techniques computationnelles au corpus saussurien peut donc constituer une aide précieuse non seulement pour les lexicographes mais également pour les experts du domaine en faisant émerger des connections qui n'apparaissent pas immédiatement de manière explicite et en suggérant ainsi des parcours alternatifs d'analyse de la pensée de l'auteur.}, KEYWORDS = {structuralisme, sémantique distributionnelle, terminologie saussurienne, lexique électronique}, URL = {https://publications.cnr.it/doc/378393}, CONFERENCE_NAME = {Atelier "Les manuscrits de Saussure, parmi d'autres. Problèmes, stratégies et solutions d'édition pour les archives numériques"}, CONFERENCE_PLACE = {Geneve}, CONFERENCE_DATE = {09-14/01/2017}, } @INPROCEEDINGS{WEINGART_2017_INPROCEEDINGS_WG_377381, AUTHOR = {Weingart, A. and Giovannetti, E.}, TITLE = {From canabo to Cannabis sativa L.: Modelling Diachronic Termino-ontological Resources in the Context of DiTMAO}, YEAR = {2017}, ABSTRACT = {The paper aims at contributing to the understanding of the Medieval Brain from a knowledge engineering perspective. As the brain is conceived as locus of cognition and knowledge in medieval medicine, we want to focus on the representation of medieval medico-botanical knowledge by means of a three-level text-termino-ontological resource. The resource is based on lemon (a model for the representation of lexica as RDF) and a set of ontologies represented in OWL and consists of (i) a medieval termino-ontological resource, (ii) a modern termino-ontological resource and (iii) a documentation corpus. It is developed and implemented within the DFG-funded project "Dictionnaire de Termes Médico-botaniques de l'Ancien Occitan" (DiTMAO). In an introductory part we will briefly introduce the aims of the project and the particularities of the corpus. The corpus consists of medical monographs in Latin script but also of so-called synonym lists in Hebrew script. These lists can be described as ancient multilingual dictionaries, in our case of Old Occitan, (Judaeo-)Arabic, Hebrew, Latin or other Romance languages and sometimes Greek and Aramaic, and they are of particular importance because the equivalent terms in other ancient languages help to determine the meaning of otherwise opaque Old Occitan terms. After introducing the three components of the resource, given some examples from our corpus, we elaborate, in the main part of paper, a solution to the problem of representing the relation between medieval medical terms or concepts and their ancient and modern correspondences. The problem concerns in particular the process of determining the terms´ meaning through the documentation of each term in corpus-external dictionaries and editions, and how this process can be represented in a comprehensive and transparent way. We propose to relate the terms of the medieval termino-ontological resource at a lexical level using relations such as synonymy or sublemma. The connections between modern and medieval terms, like a translation into modern English, will be mediated by the documentation corpus. As for modern scientific terms, we opt for an ontological connection. These types of connections will be exemplified with (mainly) plant names from our corpus. For example, a medieval term has a referent in the medieval ontology, structuring the botanic world as conceived by a "medieval brain" by giving the medieval classifications e.g. the primary qualities. This ontological entity is related to a referent of a modern scientific name, given that the documentation of the medieval term provides such information. We will argue that a clear separation of datasets (medieval and modern) allows for the diachronic study of the evolution of terminology and, more importantly for this context, paves the way for the analysis of the changes in the cognitive representation of what those terms actually refer to.}, KEYWORDS = {lexica, multi-language lexica, termino-ontological resource, ancient occitan}, URL = {https://themedievalbrain.wordpress.com/}, CONFERENCE_NAME = {The Medieval Brain Conference}, CONFERENCE_PLACE = {University of York}, CONFERENCE_DATE = {09-11/03/2017}, } @MISC{ALBANESI_2017_MISC_ABBCDGCP_427294, AUTHOR = {Albanesi, D. and Bellandi, A. and Bulleri, F. and Carniani, E. and Dattilo, D. and Giovannetti, E. and Colombo, M. and Papini, M.}, TITLE = {Traduco}, YEAR = {2017}, ABSTRACT = {il Progetto Traduzione del Talmud Babilonese ha permesso di allestire una "officina digitale" specializzata nella traduzione di testi di particolare complessità interpretativa, quali, appunto, il Talmud Babilonese. Per la realizzazione della complessa opera di traduzione è stata costituita una équipe multidisciplinare che ha coinvolto traduttori, revisori di contenuto, redattori, curatori e grafici che, attraverso la piattaforma digitale Traduco hanno potuto lavorare congiuntamente sul testo da diversi luoghi del mondo. Traduco è uno strumento web collaborativo per la traduzione assistita di testi, per lo sviluppo del quale sono state condotte ricerche specifiche, sia nell'ambito dell'Ingegneria del Software che in quello della Linguistica Computazionale. Attraverso il lavoro di ricerca, è stato possibile mettere a punto un ambiente "intelligente" di supporto alla traduzione con caratteristiche innovative. Traduco ha consentito, come side effect positivo del processo vero e proprio di traduzione, di produrre innovazione tecnologica e scientifica.}, KEYWORDS = {traduzione collaborativa, traduzione assistita dal calcolatore, linguistica computazionale, traduco, talmud babilonese}, URL = {https://publications.cnr.it/doc/427294}, } @MISC{GIOVANNETTI_2017_MISC_GD_390396, AUTHOR = {Giovannetti, E. and Del Grosso, A. M.}, TITLE = {LicoLab@LabexObvil}, YEAR = {2017}, ABSTRACT = {This talk illustrates some aspects of our research activities, specifically some outcomes carried out during designing and developing a digital environment for textual scholarship.}, KEYWORDS = {digital humanities, computational philology, software engineering}, URL = {https://publications.cnr.it/doc/390396}, } @ARTICLE{BELLANDI_2016_ARTICLE_BABG_364945, AUTHOR = {Bellandi, A. and Albanesi, D. and Benotto, G. and Giovannetti, E.}, TITLE = {Il Sistema Traduco nel Progetto Traduzione del Talmud Babilonese}, YEAR = {2016}, ABSTRACT = {Nell'ambito del Progetto Traduzione del Talmud Babilonese, l'Istituto di Linguistica Computazionale del CNR ha sviluppato Traduco, uno strumento web collaborativo con alcune caratteristiche che lo rendono particolarmente adatto alla traduzione di testi che pongono problemi interpretativi. Ad oggi, gli strumenti per la traduzione assistita (in inglese, Computer-Assisted Translation, o CAT) sono utilizzati tipicamente per la traduzione di manuali tecnici, testi legislativi o siti Web e hanno principalmente lo scopo di accelerare il processo di traduzione. Traduco riprende la maggior parte dei componenti standard di uno strumento di traduzione assistita tradizionale, ma li estende con caratteristiche specifiche necessarie per supportare l'interpretazione e la traduzione di testi complessi che pongono particolari problemi di comprensione. In questo articolo presenteremo un caso di studio specifico, relativo a un testo con queste caratteristiche: il Talmud Babilonese. Traduco include funzionalità per l'aggiunta di note, riferimenti bibliografici, annotazioni semantiche e creazione di glossari. Traduttori, revisori, redattori, supervisori e utenti finali che accedono al Sistema sono supportati nell'intero processo di traduzione, che va dall'interpretazione del testo originario alla fase ditoriale per la stampa delle traduzioni, attraverso l'uso di tecnologie di traduzione assistita, l'annotazione semantica del testo, l'arricchimento delle traduzioni con informazioni esplicative, l'esportazione delle traduzioni in XML e in TEI e l'integrazione di tecniche per il trattamento automatico della lingua. La progettazione e lo sviluppo di Traduco ha richiesto l'adozione di un approccio multidisciplinare che combina aspetti di ingegneria del software, linguistica computazionale, ingegneria della conoscenza ed editoria digitale.}, KEYWORDS = {traduco, traduzione-assistita, talmud}, PAGES = {109-126}, URL = {https://journals.openedition.org/ijcol/404}, VOLUME = {2}, PUBLISHER = {aAccademia University Press, Torino (Italia)}, ISSN = {2499-4553}, JOURNAL = {Italian Journal of Computational Linguistics}, } @INCOLLECTION{WEINGART_2016_INCOLLECTION_WG_364950, AUTHOR = {Weingart, A. and Giovannetti, E.}, TITLE = {Extending the Lemon Model for a Dictionary of Old Occitan Medico-Botanical Terminology}, YEAR = {2016}, ABSTRACT = {The article presents the adaptation of the lemon model (a model for lexica as RDF data) for a multilingual and multi- alphabetical lexicon of Old Occitan medico-botanical terminology. The lexicon is the core component of an ontology-based information system that will be constructed and implemented within the DFG-funded project "Dictionnaire des Termes Medico-botaniques de l'Ancien Occitan" (DiTMAO). The difficulties for the lemmatization raised by the particularities of the corpus (terms in Latin, Hebrew and Arabic script and corresponding terms in other ancient languages, mostly Hebrew and Arabic) can be perfectly solved by extending the basic properties of lemon and introducing domain specific vocabulary.}, KEYWORDS = {Lemon model, RDF, Multilingual, Multi-alphabetical, Historical lexicon, Medico-Botanical terminology, Old occitan, Hebrew, Arabic}, PAGES = {408-421}, URL = {http://link.springer.com/chapter/10.1007/978-3-319-47602-5_53}, VOLUME = {9989}, DOI = {10.1007/978-3-319-47602-5_53}, ISBN = {978-3-319-47601-8}, BOOKTITLE = {The Semantic Web}, EDITOR = {Sack, H. and Rizzo, G. and Steinmetz, N. and Mladenić, D. and Auer, S. and Lange, C.}, } @INPROCEEDINGS{BELLANDI_2016_INPROCEEDINGS_BBDG_364953, AUTHOR = {Bellandi, A. and Benotto, G. and Di Segni, G. and Giovannetti, E.}, TITLE = {Investigating the Application and Evaluation of Distributional Semantics in the Translation of Humanistic Texts: a Case Study}, YEAR = {2016}, ABSTRACT = {Digital Humanities are persisting ascending and the need for translating humanistic texts using Computer Assisted Translation (CAT) tools demands for a specific investigation both of the available technologies and of the evaluation techniques. Indeed, humanistic texts can present deep differences from texts that are usually translated with CAT tools, due to complex interpretative issues, the request of heavy rephrasing, and the addition of explicative parts in order to make the translation fully comprehensible to readers and, also, stylistically pleasant to read. In addition, these texts are often written in peculiar languages for which no linguistic analysis tool can be available. We faced this situation in the context of the project for the translation of the Babylonian Talmud from Ancient Hebrew and Aramaic into Italian. In this paper we describe a work in progress on the application of distributional semantics to the informing of the Translation Memory, and on the evaluation issues arising from its assessment.}, KEYWORDS = {computer-assisted translation, distributional semantics, talmud}, PAGES = {6-11}, URL = {http://www.lrec-conf.org/proceedings/lrec2016/workshops/LREC2016Workshop-NLP4TM_Proceedings.pdf}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, CONFERENCE_NAME = {2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016)}, CONFERENCE_PLACE = {Portorož, Slovenia}, CONFERENCE_DATE = {28/05/2016}, BOOKTITLE = {Proceedings of the 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016)}, } @INPROCEEDINGS{BENOTTO_2016_INPROCEEDINGS_BGM_364952, AUTHOR = {Benotto, G. and Giovannetti, E. and Marchi, S.}, TITLE = {Investigating the Application of Distributional Semantics to Stylometry}, YEAR = {2016}, ABSTRACT = {The inclusion of semantic features in the stylometric analysis of literary texts appears to be poorly investigated. In this work, we experiment with the application of Distributional Semantics to a corpus of Italian literature to test if words distribution can convey stylistic cues. To verify our hypothesis, we have set up an Authorship Attribution experiment. Indeed, the results we have obtained suggest that the style of an author can reveal itself through words distribution too.}, KEYWORDS = {NLP for Digital Humanities, Stilometry, Distributional Semantic}, PAGES = {61-65}, URL = {https://drive.google.com/open?id=0B0sEp2O7Oo7feVJLdHI3YXBxdTg}, PUBLISHER = {Accademia University Press (Torino, ITA)}, ISBN = {9788899982089}, CONFERENCE_NAME = {Third Italian Conference on Computational Linguistics}, CONFERENCE_PLACE = {Napoli}, CONFERENCE_DATE = {5-6/12/2016}, BOOKTITLE = {Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016)}, } @INPROCEEDINGS{BENOTTO_2016_INPROCEEDINGS_BGN_364353, AUTHOR = {Benotto, G. and Giovannetti, E. and Nahli, O.}, TITLE = {An application of distributional semantics for the analysis of the Holy Quran}, YEAR = {2016}, ABSTRACT = {In this contribution we illustrate the methodology and the results of an experiment we conducted by applying Distributional Semantics Models to the analysis of the Holy Quran. Our aim was to gather information on the potential differences in meanings that the same words might take on when used in Modern Standard Arabic w.r.t. their usage in the Quran. To do so we used the Penn Arabic Treebank as a contrastive corpus.}, KEYWORDS = {Distributional Semantics, the Holy Quran, Classical Arabic, Modern Standard Arabic, Contrastive Linguistics}, PAGES = {374-379}, URL = {http://ieeexplore.ieee.org/document/7805074/}, DOI = {10.1109/CIST.2016.7805074}, ISBN = {978-1-5090-0751-6}, CONFERENCE_NAME = {4th (IEEE) International Colloquium on Information Science and Technology, CiSt 2016}, CONFERENCE_PLACE = {Tangier, Morocco}, CONFERENCE_DATE = {24-26/10/2016}, BOOKTITLE = {2016 4th IEEE International Colloquium on Information Science and Technology (CiSt)}, EDITOR = {El Mohajir, M. and Chahhou, M. and Al Achhab, M. and El Mohajir, B. E.}, } @INPROCEEDINGS{PICCINI_2016_INPROCEEDINGS_PBBG_388601, AUTHOR = {Piccini, S. and Bellandi, A. and Benotto, G. and Giovannetti, E.}, TITLE = {La modellazione diacronica di risorse termino-ontologiche nell'ambito delle digital humanities: Esperimenti su clavius}, YEAR = {2016}, ABSTRACT = {In this work, we present an experiment in the modeling of a diachronic termino-ontological resource named CLAVIUS through both the N-ary relations model and the 4D-fluents approach. Some of the salient differences of these two models are discussed. The overall objective of this research is to illustrate the main advantages and disadvantages in the adoption of a given model to build diachronic resources.}, KEYWORDS = {Diachronic terminology, termino-ontological resources, n-ary models, perdurantist models}, PAGES = {205-245}, URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-85009289234\&origin=inward}, VOLUME = {1749}, PUBLISHER = {Accademia University Press (Torino, ITA)}, ISSN = {1613-0073}, ISBN = {9788899982089}, CONFERENCE_NAME = {Third Italian Conference on Computational Linguistics}, CONFERENCE_PLACE = {Napoli}, CONFERENCE_DATE = {Third Italian Conference on Computational Linguistics}, BOOKTITLE = {CEUR workshop proceedings}, } @INPROCEEDINGS{PICCINI_2016_INPROCEEDINGS_PGBR_282572, AUTHOR = {Piccini, S. and Giovannetti, E. and Bellandi, A. and Ruimy, N.}, TITLE = {Le lexique électronique de la terminologie de Ferdinand de Saussure: une première}, YEAR = {2016}, ABSTRACT = {Le Projet italien intitulé "Per un'edizione digitale dei manoscritti di Ferdinand de Saussure" a pour objectif la création d'un prototype d'édition numérique des textes du grand linguiste genevois, réalisé à partir d'une sélection de ses documents autographes. Dans ce projet, l'un des volets novateurs est la création du premier thésaurus-lexique électronique de la terminologie linguistique Saussurienne. Afin de réaliser cette base de connaissance, nous nous sommes inspirés du modèle lexical SIMPLE qui a permis le développement de vastes lexiques sémantiques informatisés, et l'avons adapté aux exigences de notre domaine de la connaissance. Le lexique réalisé a été conçu dans le but d'offrir un outil performant pour les études saussuriennes. Il fournit en effet une représentation structurée de la terminologie de Saussure, une définition du contenu sémantique de chacun des termes ainsi qu'un cadre explicite de la nature et de l'importance des liens qui les unissent. Ce faisceau d'informations devrait donc contribuer de manière significative à mieux maîtriser le vocabulaire saussurien et, partant, à éclairer certains aspects originaux de la pensée du père de la linguistique moderne.}, KEYWORDS = {Saussure, lessici computazionali, ontologie}, PAGES = {255-267}, URL = {http://www.atilf.fr/cilpr2013/actes/section-16/CILPR-2013-16-Piccini-Giovannetti-Bellandi-Ruimy.pdf}, ISBN = {979-10-91460-32-3}, CONFERENCE_NAME = {XXVII Congrès international de linguistique et de philologie romanes}, CONFERENCE_PLACE = {Nancy}, CONFERENCE_DATE = {15-20/06/2013}, BOOKTITLE = {Section 16: Projets en cours; ressources et outils nouveaux}, EDITOR = {Trotter, D. and Bozzi, A. and Fairon, C.}, } @INPROCEEDINGS{WEINGART_2016_INPROCEEDINGS_WG_364954, AUTHOR = {Weingart, A. and Giovannetti, E.}, TITLE = {A lexicon for Old Occitan medico-botanical terminology in lemon}, YEAR = {2016}, ABSTRACT = {The article presents the adaptation of the lemon model (a model for lexica as RDF data) for a multilingual and multi-alphabetical lexicon of Old Occitan medico-botanical terminology. The lexicon is the core component of an ontology-based information system that will be constructed and implemented within the DFG-funded project "Dictionnaire de Termes Médico-botaniques de l'Ancien Occitan" (DiTMAO). The difficulties for the lemmatization raised by the particularities of the corpus (terms in Latin, Hebrew and Arabic script and corresponding terms in other ancient languages, mostly Hebrew and Arabic) can be perfectly solved by extending the basic properties of lemon and introducing domain specific vocabulary.}, KEYWORDS = {lemon model, RDF, multilingual, multi-alphabetical, historical lexicon, medico-botanical terminology, Old Occitan, Hebrew, Arabic}, PAGES = {25-36}, URL = {http://www.scopus.com/record/display.url?eid=2-s2.0-84978818653\&origin=inward}, VOLUME = {1595}, PUBLISHER = {M. Jeusfeld c/o Redaktion Sun SITE, Informatik V, RWTH Aachen (Aachen, Germania)}, ISSN = {1613-0073}, CONFERENCE_NAME = {Second International Workshop on Semantic Web for Scientific Heritage (SW4SH 2016)}, CONFERENCE_PLACE = {Héraklion, Greece}, CONFERENCE_DATE = {30/05/2016}, BOOKTITLE = {CEUR workshop proceedings}, } @INPROCEEDINGS{DELGROSSO_2016_INPROCEEDINGS_DBMG_360640, AUTHOR = {Del Grosso, A. M. and Boschetti, F. and Marchi, S. and Giovannetti, E.}, TITLE = {Vantaggi dell'Astrazione attraverso l'Approccio Orientato agli Oggetti per il Digital Scholarly Editing}, YEAR = {2016}, KEYWORDS = {Object Oriented Design, ADT, Digital Textual Scholarship}, URL = {http://www.himeros.eu/aiucd2016/c33.pdf}, DOI = {10.6092/unibo/amsacta/5559}, ISBN = {978-88-942535-0-4}, CONFERENCE_NAME = {Quinto Convegno Annuale AIUCD. Edizioni digitali: rappresentazione, interoperabilità, analisi del testo e infrastrutture}, CONFERENCE_PLACE = {Ca' Dolfin, Venezia, Italia}, CONFERENCE_DATE = {7-9/09/2016}, } @INPROCEEDINGS{ALBANESI_2015_INPROCEEDINGS_ABBDG_332922, AUTHOR = {Albanesi, D. and Bellandi, A. and Benotto, G. and Di Segni, G. and Giovannetti, E.}, TITLE = {When Translation Requires Interpretation: Collaborative Computer-Assisted Translation of Ancient Texts}, YEAR = {2015}, ABSTRACT = {This paper introduces the main features of Traduco, a Web-based, collaborative Computer-Assisted Translation (CAT) tool developed to support the translation of ancient texts. In addition to the standard components offered by traditional CAT tools, Traduco includes a number of features designed to ease the translation of ancient texts, such as the Babylonian Talmud, posing specific structural, stylistic, linguistic and hermeneutical challenges.}, KEYWORDS = {Computer-Assisted Translation, Babylonian Talmud}, PAGES = {84-88}, URL = {https://publications.cnr.it/doc/332922}, ISBN = {978-1-941643-63-1}, CONFERENCE_NAME = {9th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH 2015)}, CONFERENCE_PLACE = {Bejing}, CONFERENCE_DATE = {July 30, 2015}, BOOKTITLE = {Proceedings of the 9th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities}, } @INPROCEEDINGS{BELLANDI_2015_INPROCEEDINGS_BBG_282565, AUTHOR = {Bellandi, A. and Bellusci, A. and Giovannetti, E.}, TITLE = {Computer Assisted Translation of Ancient Texts: the Babylonian Talmud Case Study}, YEAR = {2015}, ABSTRACT = {In this paper we introduce some of the features of the Computer Assisted Translation web application developed to support the translation of the Babylonian Talmud (BT) in Italian. The BT is a late antique Jewish anthological corpus, which, as other ancient texts, presents a number of hurdles related to its intrinsic linguistic and philological nature. In this work, we illustrate the solutions we adopted in the system, with particular emphasis on the Translation Memory and the translation suggestion component.}, KEYWORDS = {computer-assisted translation, Babylonian Talmud, Translation Memory}, PAGES = {287-302}, URL = {https://www.degruyter.com/view/book/9781501501289/10.1515/9781501501289.287.xml}, PUBLISHER = {De Gruyter Saur (Berlin/Munich, DEU)}, ISBN = {9781501501289}, CONFERENCE_NAME = {NLPCS 2014: 11th International Workshop on Natural Language Processing and Cognitive Science}, CONFERENCE_PLACE = {Venezia}, CONFERENCE_DATE = {27-29 ottobre 2014}, BOOKTITLE = {Natural Language Processing and Cognitive Science, Proceedings 2014}, EDITOR = {Sharp, B. and Delmonte, R.}, } @INPROCEEDINGS{ALBANESI_2015_INPROCEEDINGS_ABBG_340309, AUTHOR = {Albanesi, A. and Bellandi, A. and Benotto, G. and Giovannetti, E.}, TITLE = {Translation, Annotation and Knowledge Modelling of the Babylonian Talmud: the Traduco System}, YEAR = {2015}, ABSTRACT = {In this work, we are going to present the Traduco System, a collaborative web-based application for the translation of the Babylonian Talmud (BT) into Italian. The System has been designed around a Computer-Assisted Translation (CAT) component, constituting its core. However, Traduco is not limited to assist the translation process and to provide printing functionalities. In fact, it allows linguistic and semantic annotations and advanced searches, paving the way to the construction of a talmudic knowledge base. In order to achieve these results, the Traduco development process abided by a model that took into account aspects of Natural Language Processing and Knowledge Engineering. The component based architectural structure was implemented using the object oriented Java 2 Enterprise Edition framework.}, KEYWORDS = {Computer-Assisted Translation, Interpretation, Semantic Annotation, Babylonian Talmud}, URL = {https://dh-abstracts.library.virginia.edu/works/2399}, CONFERENCE_NAME = {Digital Humanities 2015}, CONFERENCE_PLACE = {Sydney}, CONFERENCE_DATE = {29/06-03/07/2015}, } @INPROCEEDINGS{ABRATE_2014_INPROCEEDINGS_ADGLLMMPP_282569, AUTHOR = {Abrate, M. and Del Grosso, A. M. and Giovannetti, E. and Lo Duca, A. and Luzzi, D. and Mancini, L. and Marchetti, A. and Pedretti, I. and Piccini, S.}, TITLE = {Sharing Cultural Heritage: the Clavius on the Web Project}, YEAR = {2014}, ABSTRACT = {In the last few years the amount of manuscripts digitized and made available on the Web has been constantly increasing. However, there is still a considarable lack of results concerning both the explicitation of their content and the tools developed to make it available. The objective of the Clavius on the Web project is to develop a Web platform exposing a selection of Christophorus Clavius letters along with three different levels of analysis: linguistic, lexical and semantic. The multilayered annotation of the corpus involves a XML-TEI encoding followed by a tokenization step where each token is univocally identified through a CTS urn notation and then associated to a part-of-speech and a lemma. The text is lexically and semantically annotated on the basis of a lexicon and a domain ontology, the former structuring the most relevant terms occurring in the text and the latter representing the domain entities of interest (e.g. people, places, etc.). Moreover, each entity is connected to linked and non linked resources, including DBpedia and VIAF. Finally, the results of the three layers of analysis are gathered and shown through interactive visualization and storytelling techniques. A demo version of the integrated architecture was developed.}, KEYWORDS = {language technologies for digital cultural heritage, lexica and ontologies, data visualization}, PAGES = {8}, URL = {https://publications.cnr.it/doc/282569}, ISBN = {978-2-9517408-8-4}, CONFERENCE_NAME = {LREC 2014-The 9th edition of the Language Resources and Evaluation Conference}, CONFERENCE_PLACE = {Reykjavik}, CONFERENCE_DATE = {26-31 maggio 2014}, } @INPROCEEDINGS{BELLANDI_2014_INPROCEEDINGS_BABBG_311736, AUTHOR = {Bellandi, A. and Albanesi, D. and Bellusci, A. and Bozzi, A. and Giovannetti, E.}, TITLE = {The Talmud System: a Collaborative Web Application for the Translation of the Babylonian Talmud Into Italian}, YEAR = {2014}, URL = {https://publications.cnr.it/doc/311736}, PUBLISHER = {Pisa University Press srl (Pisa, ITA)}, ISBN = {978-8-86741-472-7}, CONFERENCE_NAME = {First Italian Conference on Computational Linguistics (CLiC-it 2014)}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {9-11 dicembre 2014}, BOOKTITLE = {Proceedings of the First Italian Conference on Computational Linguistics (CLiC-it 2014)}, EDITOR = {Basili, R. and Lenci, A. and Magnini, B.}, } @INPROCEEDINGS{BELLANDI_2014_INPROCEEDINGS_BBCG_282568, AUTHOR = {Bellandi, A. and Bellusci, A. and Cappelli, A. and Giovannetti, E.}, TITLE = {Graphic Visualization in Literary Text Interpretation}, YEAR = {2014}, ABSTRACT = {We here illustrate a possible approach combining existing technologies for Natural Language Processing (NLP), Knowledge Representation and Reasoning (KRR) and Data Visualization in a coherent Decision Support System (DSS). The approach to the development of the system we are working on can be articulated in two main steps: the customization and integration of existing tools for automatic text annotation (at least linguistic, lexicographic and semantic) and the construction of a user-friendly and highly expressive GUI. The interface should allow a user to: upload her/his own text, run the desired annotation tools, visually interact with the resulting multilayered network to: i) proof-read the results of the automatic annotations, ii) manually add missing elements and/or relations between elements and, finally, iii) formulate and verify specific interpretative hypotheses.}, KEYWORDS = {Computational Hermeneutics, Text processing, Knowledge Representation and Reasoning, Data Visualization}, PAGES = {392-397}, URL = {https://publications.cnr.it/doc/282568}, DOI = {10.1109/IV.2014.62}, PUBLISHER = {IEEE (New York, USA)}, CONFERENCE_NAME = {18th International Conference on Information Visualisation}, CONFERENCE_PLACE = {Parigi}, CONFERENCE_DATE = {15, 16, 17, 18 luglio 2014}, BOOKTITLE = {Information Visualisation}, EDITOR = {Banissi, E. and Bannatyne, M. W. M. and Marchese, F. T. and Sarfraz, M. and Ursyn, A. and Venturini, G. and Wyeld, T. G. and Cvek, U. and Trutschl, M. and Grinstein, G. and Geroimenko, V. and Kenderdine, S. and Bouali, F.}, } @INPROCEEDINGS{BELLANDI_2014_INPROCEEDINGS_BBCG_282571, AUTHOR = {Bellandi, A. and Bellusci, A. and Carniani, E. and Giovannetti, E.}, TITLE = {Content Elicitation: Towards a New Paradigm for the Analysis and Interpretation of Texts}, YEAR = {2014}, ABSTRACT = {In this paper we show how semantic technologies can be exploited, with the help of user friendly interfaces, to identify and structure the knowledge embedded in literary texts. The proposed approach, that we have called Content Elicitation, supports the experts in defining hierarchical and associative relationships between semantically annotated chunks of text denoting relevant entities, allowing visual structuring of knowledge, which can be edited by different experts in a collaborative way. This knowledge, formally coded as an ontology, can then be used by scholars and students as a guide for the analysis of the text and for the discovery of potential novel interpretations. We are testing and evaluating this approach on the Babylonian Talmud, due to its historical, linguistic, semantic and structural richness.}, KEYWORDS = {semantic annotation, knowledge representation, text ontology, content elicitation, literary computing, data visualization}, URL = {https://publications.cnr.it/doc/282571}, DOI = {10.2316/P.2014.810-031}, PUBLISHER = {Acta press (Calgary, CAN)}, CONFERENCE_NAME = {The 13th IASTED International Conference on Software Engineering}, CONFERENCE_PLACE = {Innsbruck}, CONFERENCE_DATE = {17-19 febbraio 2014}, EDITOR = {Hamza, M. H.}, } @INPROCEEDINGS{BELLUSCI_2014_INPROCEEDINGS_BBBCGM_311735, AUTHOR = {Bellusci, A. and Bellandi, A. and Benotto, G. and Cappelli, A. and Giovannetti, E. and Marchi, S.}, TITLE = {Towards a Decision Support System for Text Interpretation}, YEAR = {2014}, ABSTRACT = {This article illustrates the first steps towards the implementation of a Decision Support System aimed to recreate a research environment for scholars and provide them with computational tools to assist in the processing and interpretation of texts. While outlining the general characteristics of the system, the paper presents a minimal set of user requirements and provides a possible use case on Dante's Inferno.}, KEYWORDS = {DDS, XML, text interpretation, literary computing}, PAGES = {58-62}, URL = {http://clic.humnet.unipi.it/proceedings/vol1/CLICIT2014112.pdf}, VOLUME = {I}, DOI = {10.12871/CLICIT2014118}, ISBN = {9788867414727}, CONFERENCE_NAME = {First Italian Conference on Computational Linguistics (CLiC-it 2014)}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {9-11 dicembre 2014}, BOOKTITLE = {Proceedings of the First Italian Conference on Computational Linguistics (CLiC-it 2014)}, EDITOR = {Basili, R. and Lenci, A. and Magnini, B.}, } @INPROCEEDINGS{PEDRETTI_2014_INPROCEEDINGS_PDGMPALM_340200, AUTHOR = {Pedretti, I. and Del Grosso, A. and Giovannetti, E. and Mancini, L. and Piccini, S. and Abrate, M. and Lo Duca, A. and Marchetti, A.}, TITLE = {The Clavius on the Web Project: Digitization, Annotation and Visualization of Early Modern Manuscripts}, YEAR = {2014}, ABSTRACT = {This paper describes the full procedure adopted in the context of the Clavius on the Web project, which aims to help Web users to appraise the importance of specific manuscripts by going beyond their digital reproduction. The proposed approach is based on the multilayered explication of linguistic, lexical and semantic data representing the innermost nature of the analyzed manuscripts. The final purpose of the project is to gather and display the results of the three layers of analysis through interactive visualization techniques and export them as Linked Data. All the analyses rely on the XML/TEI encoding of the text, followed by a CTS-based tokenization. As a working example for this paper, the analysis of a portion of a manuscript provided by Historical Archives of the Pontifical Gregorian University will be illustrated. The text is a letter written in Latin and sent by Botvitus Nericius to Christophorus Clavius in 1598 from Madrid.}, KEYWORDS = {Clavius, Data Visualization, Early Modern Manuscripts, Lexica and Ontologies, Linked Open Data, NLP for Latin, Promotion of Cultural Heritage}, PAGES = {7}, URL = {http://dl.acm.org/citation.cfm?id=2802636}, DOI = {10.1145/2802612.2802636}, PUBLISHER = {ACM, Association for computing machinery (New York, USA)}, ISBN = {978-1-4503-3295-8}, CONFERENCE_NAME = {Third AIUCD Annual Conference on Humanities and Their Methods in the Digital Ecosystem (AIUCD '14)}, CONFERENCE_PLACE = {Bologna}, CONFERENCE_DATE = {18-19/09/2014}, BOOKTITLE = {Proceedings of the Third AIUCD Annual Conference on Humanities and Their Methods in the Digital Ecosystem (AIUCD '14)}, EDITOR = {Tomasi, F. and Del Turco, R. R. and Tammaro, A. M.}, } @INPROCEEDINGS{PICCINI_2014_INPROCEEDINGS_PRG_282583, AUTHOR = {Piccini, S. and Ruimy, N. and Giovannetti, E.}, TITLE = {Il primo lessico elettronico della terminologia saussuriana}, YEAR = {2014}, ABSTRACT = {Il lavoro che intendiamo presentare si iscrive all'interno di un Progetto di Ricerca Nazionale finanziato dal governo italiano, intitolato "Per una edizione digitale dei manoscritti di Ferdinand de Saussure", e volto a creare un prototipo di edizione digitale degli scritti autografi del grande linguista ginevrino. A tal fine, ogni manoscritto è stato digitalizzato, classificato e dotato di un link ipertestuale che rimanda alla sua trascrizione. Un sistema di gestione dei testi permette di consultare e annotare il singolo manoscritto e di effettuare studi filologici e critici sul corpus digitalizzato. Le concordanze per forma e per lemma prodotte per l'insieme dei testi forniscono un insieme di termini caratteristici dei quali viene descritta la semantica. Accanto alla realizzazione di tale piattaforma filologica digitale, uno degli aspetti innovativi del progetto consiste nella creazione del primo thesaurus-lessico elettronico della terminologia linguistica saussuriana. Quest'ultima riceve per la prima volta una rappresentazione strutturata, con una definizione del contenuto semantico di ciascuno dei termini chiave del pensiero del maestro ginevrino ed un quadro esplicito della natura e dell'importanza dei legami che li uniscono. Tale fascio di informazioni dovrebbe contribuire in modo significativo a meglio conoscere ed interpretare il pensiero del padre della linguistica moderna. L'architettura del lessico è ispirata al modello lessicale SIMPLE. Tra i modelli lessicali di maggior rilievo (WordNet, EuroWordNet, ItalWordNet, FrameNet, Pattern Dictionary, SIMPLE e Brandeis Semantic Ontology) esso è apparso essere il più adeguato, in quanto si distingue per alcuni importanti ed innovati aspetti. Il modello SIMPLE, infatti, ha permesso la realizzazione di lessici elettronici multilivello armonizzati per dodici lingue europee, imponendosi così come standard de facto nell'ambito della Lessicografia Computazionale. Successivamente ha fortemente ispirato lo standard ISO per i lessici del TAL Lexical Markup Framework. La strutturazione del lessico ha necessitato anzitutto della creazione di una ontologia lessicale di dominio. A tal fine è stato adottato un approccio centrifugo: in un primo momento sono stati identificati i concetti centrali del dominio di interesse, i quali sono stati poi generalizzati o specificati. L'ontologia così modellizzata è attualmente costituita da 43 tipi semantici ed ha una profondità di 4 livelli. Alcune classi semantiche sono state poi ulteriormente "specificate" in termini di tratti e/o relazioni semantiche obbligatorie (definitorie). Un insieme di cinquantotto relazioni semantiche permette di collegare le istanze delle differenti classi ontologiche, mentre trentadue tratti semantici codificano informazioni tipiche di una classe semantica nella sua interezza o di una specifica istanza. La semantica lessicale di ciascuna delle istanze di una classe ontologica è rappresentata in una entrata lessicale, nella quale una ed una sola accezione di un termine, semplice o complesso, viene riccamente definita attraverso un vasto insieme di informazioni formalizzate ed altamente strutturate, che coprono un ampio ventaglio di aspetti semantici. Il senso analizzato è anzitutto associato alla definizione data da Saussure stesso, e laddove non disponibile, a quelle di R. Godel e R. Engler. Per ogni lemma vengono specificati anche il periodo di attestazione, le fonti nelle quali occorre, la sua frequenza di occorrenza e le collocazioni nelle quali appare. La classificazione ontologica del termine rappresenta un dato essenziale al quale si aggiungono l'informazione concernente il dominio d'uso, il tipo di evento denotato (qualora si tratti di un evento), dei tratti semantici distintivi e una vasta rete di relazioni semantico-lessicali. Il modello lessicale adottato, infatti, conferisce una attenzione particolare ai legami che esistono tra i differenti termini. La multidimensionalità intrinseca al senso di ogni lemma è colta e formalizzata attraverso un insieme di relazioni semantiche specifiche del modello SIMPLE e ispirate alla Struttura Qualia della teoria del Lessico Generativo. Esse offrono un quadro preciso della natura dei legami (intra ed extra categoriali) che sussistono tra le unità lessicali contenute nella base di dati sia sull'asse paradigmatico (iperonimia, iponimia, meronimia ed olonimia) sia sull'asse sintagmatico (fornendo in particolare informazioni sull'origine e la funzione dell'entità denotata). Inoltre, accanto alle classiche relazioni di sinonimia, antonimia e di derivazione morfologica, sono state create delle relazioni specifiche, al fine di formalizzare nel modo più preciso possibile i legami particolari esistenti tra i termini del dominio della conoscenza e più generalmente la sua organizzazione concettuale. Dei termini predicativi contenuti nel lessico viene descritta anche la struttura argomentale con indicazioni sul ruolo semantico e sulle restrizioni semantiche degli argomenti introdotti. Allo stato attuale, la popolazione del lessico è costituita da 500 entrate lessicali (379 nomi, 113 aggettivi e 8 verbi): si tratta principalmente dei termini proposti da Godel e Engler e di alcune parole-chiave estratte dagli Écrits de linguistique générale. In una fase successiva verrà integrata la nuova terminologia dei manoscritti attualmente studiati. In una prima fase i dati lessicali sono stai gestiti in una piattaforma MS ACCESS. Più recentemente, per esigenze di standardizzazione ed interoperabilità, è stata effettuata una migrazione sulla piattaforma Protégé-OWL. Owl è, infatti, il linguaggio standard del W3C per la rappresentazione e la condivisone di ontologie sul Web. Il sistema di gestione Access, tuttavia, non è stato abbandonato: il lessico, attualmente, è ospitato in entrambe le piattaforme grazie ad un software che consente la perfetta sincronizzazione dei dati. Questa provvisoria "doppia ubicazione" permette, intanto, di sfruttare in modo ottimale le potenzialità dei due sistemi di gestione. Una tale strutturazione informatizzata dei dati lessicali offre numerosi vantaggi. In fase di creazione del lessico, essa permette uno sviluppo collaborativo rigoroso, anche a distanza, e lo stoccaggio di una grande quantità di dati; favorisce una rappresentazione sistematica dei fenomeni linguistici ed assicura la coerenza e la completezza dell'informazione codificata. Inoltre, consente di operare costanti controlli di coerenza formale dell'informazione e di effettuare delle modifiche o delle correzioni sull'insieme dei dati. La strutturazione multidimensionale dei concetti del dominio di conoscenza e la rappresentazione semantica altamente strutturata, ricca, diversificata ed espressiva ne fanno uno strumento di ricerca lessicale particolarmente performante. Varie tipologie di ricerca possono essere effettuate molto semplicemente e rapidamente su qualsiasi dato memorizzato, sia esso una relazione, un tratto o una unità semantica e questi dati possono essere interrogati sia singolarmente sia in combinazione. Si ha quindi la possibilità di estrarre gruppi di unità lessicali che condividono una data proprietà o una combinazione di proprietà, secondo dei criteri stabiliti dallo studioso in relazione alle esigenze della sua ricerca. A titolo di esempio, verranno presentate alcune delle numerose ricerche che possono essere effettuate sui dati lessicali all'interno della base di dati. A nostro parere, il thesaurus-lessico semantico della terminologia saussuriana costituisce, per i motivi esposti, uno strumento di grande utilità per gli esperti del settore. Inoltre, l'organizzazione strutturata della conoscenza lessicale, favorendo la ricerca semantica, dovrebbe contribuire in modo significativo ad una più approfondita conoscenza del vocabolario del maestro e pertanto degli aspetti più complessi ed originali del suo pensiero.}, KEYWORDS = {Saussure, SIMPLE, lessici computazionali}, URL = {https://publications.cnr.it/doc/282583}, CONFERENCE_NAME = {XXXVII Convegno della Società Italiana di Glottologia, "Il lessico nella teoria e nella storia linguistica"}, CONFERENCE_PLACE = {Firenze}, CONFERENCE_DATE = {25-27/10/2012}, } @INPROCEEDINGS{ABRATE_2014_INPROCEEDINGS_ADGLMMPP_282564, AUTHOR = {Abrate, M. and Del Grosso, A. M. and Giovannetti, E. and Lo Duca, A. and Marchetti, A. and Mancini, L. and Pedretti, I. and Piccini, S.}, TITLE = {Il Progetto Clavius on the Web: tecnologie linguistico-semantiche al servizio del patrimonio documentale e degli archivi storici}, YEAR = {2014}, ABSTRACT = {L'obiettivo del progetto Clavius on the Web è quello di valorizzare una parte dei manoscritti conservati dall'Archivio storico della Pontificia Università Gregoriana (APUG). Il progetto prende in esame alcuni manoscritti relativi a Christophorus Clavius (1538-­1612), matematico e astronomo gesuita. I manoscritti sono digitalizzati, trascritti, tradotti e analizzati dal punto di vista linguistico, lessicale e semantico. La terminologia e le entità di dominio individuate nel testo sono strutturate in un lessico e una ontologia, e collegate a risorse già disponibili sulla Rete secondo i principi dei Linked Data. La loro visualizzazione sul Web è implementata mediante tecniche di Data Visualization: la prima si basa sulla corrispondenza tra testo, traduzione e immagine mentre la seconda ha lo scopo di mostrare i contenuti delle analisi, con particolare enfasi alla navigazione delle risorse lessicali e ontologiche prodotte durante le varie fasi.}, URL = {https://publications.cnr.it/doc/282564}, CONFERENCE_NAME = {AIUCD 2014-Terzo convegno annuale: La metodologia della ricerca umanistica nell'ecosistema digitale}, CONFERENCE_PLACE = {Bologna}, CONFERENCE_DATE = {18-19 Settembre 2014}, BOOKTITLE = {AIUCD2014-La metodologia della ricerca umanistica nell'ecosistema digitale-Abstracts 3rd annual conference, 18-19 settembre 2014}, EDITOR = {Rossi, F. and Tomasi, F.}, } @ARTICLE{NAHLI_2013_ARTICLE_NG_282561, AUTHOR = {Nahli, O. and Giovannetti, E.}, TITLE = {Computational contributions for Arabic language processing-Part II. Lisan al-'arab as a source of lexical and morphological knowledge}, YEAR = {2013}, ABSTRACT = {The following sections illustrate a part of the study on the morphology of the Arabic language which is carried on within the framework of the ERC project Greek into Arabic. Philosophical Concepts and Linguistic Bridges ADG 249431. We used the Arabic lexicographic encyclopaedia Lisan al-'arab and, thanks to the regularity of its structure, we developed a system for the extraction of morphologically labelled word sequences, to be exploited for morphological analysis purposes.}, KEYWORDS = {Arabic morphology, Arabic morphological analysis, Arabic lexicography, Natural Language Processing}, PAGES = {207-210}, URL = {https://publications.cnr.it/doc/282561}, VOLUME = {3}, PUBLISHER = {CNR, Istituto di Linguistica Computazionale (Pisa, Italia)}, ISSN = {2239-012X}, JOURNAL = {Studia graeco-arabica}, } @INCOLLECTION{RUIMY_2013_INCOLLECTION_RPGB_272216, AUTHOR = {Ruimy, N. and Piccini, S. and Giovannetti, E. and Bellandi, A.}, TITLE = {Lessicografia Computazionale e Terminologia Saussuriana}, YEAR = {2013}, PAGES = {161-179}, URL = {https://publications.cnr.it/doc/272216}, PUBLISHER = {Edizioni dell'Orso (Alessandria, ITA)}, ISBN = {978-88-6274-478-2}, BOOKTITLE = {Guida per un'edizione digitale dei manoscritti di Ferdinand de Saussure}, } @TECHREPORT{DELGROSSO_2013_TECHREPORT_DGP_354193, AUTHOR = {Del Grosso, A. M. and Giovannetti, E. and Piccini, S.}, TITLE = {Definizione del modello di filologia computazionale}, YEAR = {2013}, ABSTRACT = {Il documento illustra il lavoro di analisi condotto durante la prima fase del progetto Clavius on the Web. Nelle sezioni del documento si descrivono le modalità secondo le quali il modello generale della piattaforma di gestione dei testi verrà implementato partendo dalle esigenze degli studiosi dei manoscritti originali di Clavius digitalizzati e messi a raffronto con i file di trascrizione.}, KEYWORDS = {Clavius, Clavius on the web, Literary Computing, Computational Philology, Lexica, Latin, Semantic Web}, URL = {http://claviusontheweb.it/}, } @INPROCEEDINGS{BIANCHI_2012_INPROCEEDINGS_BTG_282573, AUTHOR = {Bianchi, E. and Tavosanis, M. and Giovannetti, E.}, TITLE = {Creation of a bottom-up corpus-based ontology for Italian Linguistics}, YEAR = {2012}, ABSTRACT = {This paper describes the steps of construction of a shallow lexical ontology of Italian Linguistics in Italian, set to be used by a meta-search engine for query refinement. The ontology was constructed with the software Protege 4.0.2 and encoded in OWL format; its construction has been carried out following the steps described in the well-known Ontology Learning From Text (OLFT) layer cake. The starting point was the automatic term extraction from a corpus of web documents concerning the domain of interest (304,000 words); as regards corpus construction, we describe the main criteria of the web documents selection and its critical points, concerning the definition of user profile and of degrees of specialisation. We then describe the process of term validation and construction of a glossary of terms of Italian Linguistics; afterwards, we outline the identification of synonymic chains and the main criteria of ontology design: top classes of ontology are Concept (containing taxonomy of concepts) and Term (containing terms of the glossary as instances), while concepts are linked through part-whole and involved-role relation, both borrowed from Wordnet. Finally, we show some examples of the application of the ontology for query refinement.}, KEYWORDS = {Ontologies, Italian Linguistics, Query refinement}, PAGES = {2641-2647}, URL = {https://publications.cnr.it/doc/282573}, PUBLISHER = {European Language Resources Association ELRA (Paris, FRA)}, CONFERENCE_NAME = {LREC 2012-Eight International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Istanbul}, CONFERENCE_DATE = {23-25 maggio 2012}, BOOKTITLE = {Language Resources and Evaluation}, } @INPROCEEDINGS{RUIMY_2012_INPROCEEDINGS_RPG_220294, AUTHOR = {Ruimy, N. and Piccini, S. and Giovannetti, E.}, TITLE = {Defining and Structuring Saussure's Terminology}, YEAR = {2012}, ABSTRACT = {In the framework of the Italian project 'For a digital edition of Ferdinand de Saussure's manuscripts', an electronic thesaurus of Saussure's terminology is being built, which includes new terms extracted from recently found manuscripts. The lexical model on which it is grounded is a customized version of the SIMPLE model. In this paper, an overview of the customization process is provided, with a special focus on the steps taken for designing a domain-specific ontology as well as on the creation of additional semantic relations and features. Lexical entries are illustrated and the potential of a structured organization of semantic knowledge for gaining a wider understanding of the overall domain terminology is highlighted.}, KEYWORDS = {Computational Lexicon}, PAGES = {828-833}, URL = {http://www.euralex.org/elx_proceedings/Euralex2012/pp828-833%20Ruimy,%20Piccini%20and}, CONFERENCE_NAME = {15th EURALEX International Congress (EURALEX2012)}, CONFERENCE_PLACE = {Oslo, Norway}, CONFERENCE_DATE = {07-11 / 08 2012}, } @INPROCEEDINGS{RUIMY_2012_INPROCEEDINGS_RPG_220309, AUTHOR = {Ruimy, N. and Piccini, S. and Giovannetti, E.}, TITLE = {Les Outils Informatiques au Service de la Terminologie Saussurienne}, YEAR = {2012}, ABSTRACT = {Bien que l'oeuvre de Ferdinand de Saussure ait été diffusée à travers le monde, sa pensée a été en grande partie reconstruite et interprétée par ses étudiants et disciples. Ses écrits authentiques revêtent pourtant, de notre point de vue, une importance fondamentale : ils mettent en lumière l'attention que Saussure accorde à la terminologie linguistique. Lui-même utilise souvent un vocabulaire particulier. Il forge des néologismes ou confère un sens nouveau à des mots existants, il emploie quelques termes de façon éphémère, change la dénotation de certains concepts au fil du temps, créant ainsi une terminologie qui lui est propre. Dans cet article, nous présentons le premier thésaurus-lexique électronique de la terminologie linguistique saussurienne, en cours de création. La population de ce lexique est constituée par une nomenclature mise à jour, comprenant non seulement la terminologie répertoriée par Godel et Engler mais également de nouveaux termes extraits de manuscrits actuellement à l'étude. À travers ce lexique, nous nous proposons de fournir une représentation structurée de la terminologie saussurienne, de définir le contenu sémantique de chacun des termes ainsi que la nature des relations qui les unissent. À cet effet, nous avons choisi de customiser le modèle lexical SIMPLE qui, dans le panorama de la Lexicographie Computationnelle, s'est imposé comme standard de facto et offre une représentation sémantique hautement structurée des unités lexicales. Le processus de customisation du modèle de base s'est tout d'abord focalisé sur la conception d'une ontologie lexicale de domaine (ontologie SIMPLE_FdS), et sa traduction dans le langage de représentation d'ontologie Web OWL. Puis, les deux autres composants du modèle de base, i.e. un réseau de relations sémantiques et un ensemble de traits sémantiques, ont été également adaptés aux exigences du domaine traité. Les moyens expressifs jugés appropriés pour rendre compte de la terminologie saussurienne ont été retenus tandis que des traits et relations spécifiques ont été créés afin d'exprimer des propriétés et des liens qui caractérisent l'organisation conceptuelle de ce domaine de la connaissance. Le lexique est ici illustré par des exemples d'entrées lexicales et le potentiel de la base de connaissance par des requêtes sur les données mémorisées. L'organisation structurée de la connaissance lexicale et la richesse de la représentation sémantique font de ce lexique un outil de recherche sémantique particulièrement performant et qui devrait contribuer de manière significative à mieux maîtriser le vocabulaire saussurien et à éclairer certains aspects originaux de la pensée du maître genevois.}, KEYWORDS = {Computational Lexicon}, PAGES = {1043-1056}, URL = {http://www.shs-conferences.org/articles/shsconf/abs/2012/01/shsconf_cmlf12_000294/shs}, DOI = {10.1051/shsconf/20120100294}, PUBLISHER = {EDP Sciences (Les Ulis Cedex, FRA)}, ISBN = {978-2-7598-0783-3}, CONFERENCE_NAME = {3e Congrès Mondial de Linguistique Française (CMLF 2012)}, CONFERENCE_PLACE = {Lione-Francia}, CONFERENCE_DATE = {04-07 / 07 2012}, BOOKTITLE = {3e Congrès Mondial de Linguistique Française}, } @INPROCEEDINGS{PICCINI_2012_INPROCEEDINGS_PRG_282584, AUTHOR = {Piccini, S. and Ruimy, N. and Giovannetti, E.}, TITLE = {Structuring a specific domain: an electronic thesaurus of Ferdinand de Saussure's terminology}, YEAR = {2012}, ABSTRACT = {Although Ferdinand de Saussure's work has been disseminated all over the world, his thought was mainlyreconstructed and interpreted by his students and disciples. His authentic writings are however of paramount importance as they highlight the complexity of the philosophical and semiological system Saussure developed and the attention he payed to linguistic terminology. The great Genevan linguist himself often used a peculiar vocabulary. He forged neologisms or conferred a new meaning to existing words, used a few terms ephemerally, changed the denotation of some concepts over the years, so to create his own idiosyncratic terminology, which is now at the base of modern linguistics. In this paper, we present the first electronic thesaurus-lexicon of the Saussurean linguistic terminology that is being developed in the framework of the ongoing Italian project 'For a digital edition of Ferdinand de Saussure's manuscripts'. The lexicon population consists of an updated nomenclature, encompassing not only the terminology gathered by two famous Saussurean scholars, Robert Godel and Rudolf Engler, but also new terms extracted from recently found manuscripts under study. In the lexicon, the overall structure of Saussure's terminology is made explicit and the semantic import of its component terms as well as the nature and relevance of their relationships are defined. The lexical model, on which the thesaurus is grounded, is a customized version of the SIMPLE model, a de facto standard in the domain of Computational Lexicography that enables a highly structured representation of lexical knowledge. The first stage of the customization process consisted in designing and translating into the Web Ontology Language OWL the central component of the SIMPLE_FdS model, i.e. a domain-specific lexical ontology that would structure Saussure's terminology. The two other building blocks of the root model, i.e. a network of semantic relations and a set of semantic features, were adapted in order to meet the requirements of the domain of interest. The expressive means deemed suitable for our domain were maintained whereas additional specific features and relations were created to account for term properties and relationships peculiar to the conceptual organization of this domain of knowledge. So far, 375 terms were endowed with a rich semantic description. In the extended paper, examples of lexical entries will be provided and many interesting possibilities of lexical investigation will be pointed out. Information retrieval queries may in fact be formulated using any single piece of information encoded, be it a semantic relation, a feature or a lexical unit. Such an electronic thesaurus-lexicon, based on a multidimensional structuring of concepts and a large network of semantic relations among terms, is therefore, in our opinion, a most valuable lexical research tool. It is our deep conviction that it will contribute to better master some of Saussure's reflections and to gain a wider understanding of the overall domain terminology. It might therefore help shading light on original aspectsof the author's thought.}, KEYWORDS = {Saussure, terminologia, lessici computazionali}, PAGES = {1}, URL = {https://publications.cnr.it/doc/282584}, CONFERENCE_NAME = {45th Annual Meeting of the Societas Linguistica Europaea (SLE)}, CONFERENCE_PLACE = {Stoccolma}, CONFERENCE_DATE = {29/08/2012-01/09/2012}, BOOKTITLE = {45th Annual Meeting of the Societas Linguistica Europae, Book of Abstracts}, EDITOR = {Cornillie, B. and Pascual, M. S. S.}, } @TECHREPORT{BOZZI_2012_TECHREPORT_BGBNMPRD_390781, AUTHOR = {Bozzi, A. and Giovannetti, E. and Boschetti, F. and Nahli, O. and Marchi, S. and Piccini, S. and Ruimy, N. and Del Grosso, A. M.}, TITLE = {Greek into Arabic: contents, technologies and (humanistic and scientific) applications of a new software}, YEAR = {2012}, ABSTRACT = {This contribution aims to describe the methodological approach to Digital Philology by means of the G\&A Web Application. It also shows running examples for the: 1) Visualization and ordering of parallel texts subdivided in pericopes; 2) Linguistic annotations; 3) Scholarly comments; and 4)Search functions}, KEYWORDS = {digital philology, computational philology, software engineering, Greek into Arabic, Computational linguistics}, URL = {https://publications.cnr.it/doc/390781}, } @INPROCEEDINGS{GIOVANNETTI_2011_INPROCEEDINGS_GM_282633, AUTHOR = {Giovannetti, E. and Marchi, S.}, TITLE = {Cross-Language Boosting in Pattern-based Semantic Relation Extraction from Text}, YEAR = {2011}, ABSTRACT = {In this work we propose a novel technique called "Cross-Language Boosting" (C-LB), aimed at increasing the accuracy of pattern-based semantic relation extraction systems: given a pair of terms expressed in a "Target Language" (e.g. in Italian), we can translate the terms in a "Support Language" (e.g. in English) and apply the translated term pair to reliable lexico-syntactic patterns expressed in that language to increase the accuracy of the system. Experiments have been conducted by comparing the results obtained by the SemRelEx system, a hybrid unsupervised system for semantic relation extraction from texts, with and without the support of the C-LB technique, applied to a set of candidate semantically related term pairs automatically extracted from a corpus in the History of Art domain.}, KEYWORDS = {Computational Linguistics, Cross Language, semantic relation extraction systems, Ontology Learning from Text}, PAGES = {29-36}, URL = {https://web.archive.org/web/20121101020859/http://www.proceedings2011.cla-conf.info/}, ISBN = {9788360810477}, CONFERENCE_NAME = {Computational Linguistics Application Conference-CLA 2011}, CONFERENCE_PLACE = {Jachranka, Poland}, CONFERENCE_DATE = {17-19 ottobre 2011}, BOOKTITLE = {Proceedings of the Computational Linguistics-Applications Conference}, EDITOR = {Jassem, K. and Fuglewicz, P. and Piasecki, M. and Przepiorkowski, A.}, } @INPROCEEDINGS{GIOVANNETTI_2010_INPROCEEDINGS_G_84798, AUTHOR = {Giovannetti, E.}, TITLE = {An unsupervised approach for semantic relation interpretation}, YEAR = {2010}, ABSTRACT = {In this work we propose a hybrid unsupervised approach for semantic relation extraction from Italian and English texts. The system takes as input pairs of "distributionally similar" terms, possibly involved in a semantic relation. To validate and label the anonymous relations holding between the terms in input, the candidate pairs of terms are looked for on the Web in the context of reliable lexico-syntactic patterns. This paper focuses on the definition of the patterns, on the measures used to assess the reliability of the suggested specific semantic relation and on the evaluation of the implemented system.}, KEYWORDS = {Information Extraction, Information Retrieval, Knowledge Representation, Ontologies}, PAGES = {3811-3816}, URL = {https://publications.cnr.it/doc/84798}, PUBLISHER = {European language resources association (ELRA) (Paris, FRA)}, ISBN = {2-9517408-6-7}, CONFERENCE_NAME = {Seventh International Conference on Language Resources and Evaluation}, CONFERENCE_PLACE = {Valletta, Malta}, CONFERENCE_DATE = {19-21 maggio 2010}, BOOKTITLE = {Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)}, EDITOR = {Calzolari, N. and Choukri, K. and Maegaard, B. and Mariani, J. and Odijk, J. and Piperidis, S. and Rosner, M. and Tapias, D.}, } @TECHREPORT{DELGROSSO_2010_TECHREPORT_DG_354196, AUTHOR = {Del Grosso, A. M. and Giovannetti, E.}, TITLE = {Sistema di gestione della banca dati lessicale}, YEAR = {2010}, ABSTRACT = {Il documento descrive l'analisi e lo studio preliminare svolto sul sistema di gestione della banca dati lessicale sviluppato nell'ambito dei progetti PAROLE, SIMPLE e CLIPS}, KEYWORDS = {Lessico elettronico, piattaforma web}, PAGES = {21}, URL = {https://publications.cnr.it/doc/354196}, } @TECHREPORT{PIRRELLI_2010_TECHREPORT_PLMDGM_367784, AUTHOR = {Pirrelli, V. and Lenci, A. and Montemagni, S. and Dell'Orletta, F. and Giovannetti, E. and Marchi, S.}, TITLE = {ConnectToLife (modulo semantico)-Rapporto tecnico finale}, YEAR = {2010}, ABSTRACT = {Il presente documento costituisce il rapporto tecnico finale del progetto Connect-To-Life (modulo semantico) relativo alle attività svolte dall'unità ILC-CNR.}, KEYWORDS = {annotazione linguistica, estrazione di termini, clustering semantico, trattamento automatico della lingua, costruzione di ontologie}, PAGES = {16}, URL = {https://publications.cnr.it/doc/367784}, } @ARTICLE{BAGLIONI_2008_ARTICLE_BGMRS_68449, AUTHOR = {Baglioni, M. and Giovannetti, E. and Masserotti, M. V. and Renso, C. and Spinsanti, L.}, TITLE = {Ontology-supported Querying of Geographical Databases}, YEAR = {2008}, ABSTRACT = {Querying geographical information systems has been recognized as a difficult task for non-expert users. Furthermore, user queries are often characterized by semantic aspects not directly managed by traditional spatial databases or GIS. Examples of such semantic geospatial queries are the use of implicit spatial relations between objects, or the reference of domain concepts not explicitly represented in data. To handle such queries, we envisage a system that translates natural language queries into spatial SQL statements on a database, thus improving standard GIS with new semantic capabilities. Within this general objective, the contribution of this article is to introduce a methodology to handle semantic geospatial queries issued over a spatial database. This approach captures semantics from an ontology built upon the spatial database and enriched by domain concepts and properties specifically defined to represent the localization of objects. Some examples of the use of the methodology in the urban domain are presented.}, KEYWORDS = {H. 2. 8 Database Applications, Ontology extraction, Spatial databases}, PAGES = {31-44}, URL = {https://publications.cnr.it/doc/68449}, VOLUME = {12 (suppl. 1)}, PUBLISHER = {Blackwell (Oxford, Regno Unito)}, ISSN = {1467-9671}, JOURNAL = {Transactions in GIS (Online)}, } @INPROCEEDINGS{GIOVANNETTI_2008_INPROCEEDINGS_GMM_84706, AUTHOR = {Giovannetti, E. and Marchi, S. and Montemagni, S.}, TITLE = {Combining statistical techniques and lexico-syntactic patterns for semantic relations extraction from text}, YEAR = {2008}, ABSTRACT = {We describe here a methodology to combine two different techniques for Semantic Relation Extraction from texts. On the one hand, generic lexicosyntactic patterns are applied to the linguistically analyzed corpus to detect a first set of pairs of co-occurring words, possibly involved in "syntagmatic" relations. On the other hand, a statistical unsupervised association system is used to obtain a second set of pairs of "distributionally similar" terms, that appear to occur in similar contexts, thus possibly involved in "paradigmatic" relations. The approach aims at learning ontological information by filtering the candidate relations obtained through generic lexico-syntactic patterns and by labelling the anonymous relations obtained through the statistical system. The resulting set of relations can be used to enrich existing ontologies and for semantic annotation of documents or web pages.}, KEYWORDS = {Ontology Learning from Text, Semantic Relation Extraction, Lexico-syntactic Patterns, Distributional Similarity}, URL = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-426/swap2008_submission_54.pdf}, CONFERENCE_NAME = {SWAP 2008-Semantic Web Applications and Perspectives}, CONFERENCE_PLACE = {Roma}, CONFERENCE_DATE = {15-17 December 2008}, EDITOR = {Gangemi, A. and Keizer, J. and Presutti, V. and Stoermer, H.}, } @INPROCEEDINGS{GIOVANNETTI_2008_INPROCEEDINGS_GMMB_84726, AUTHOR = {Giovannetti, E. and Marchi, S. and Montemagni, S. and Bartolini, R.}, TITLE = {Ontology Learning and Semantic Annotation: a Necessary Symbiosis}, YEAR = {2008}, ABSTRACT = {Semantic annotation of text requires the dynamic merging of linguistically structured information and a "world model", usually represented as a domain-specific ontology. On the other hand, the process of engineering a domain-ontology through semi-automatic ontology learning system requires the availability of a considerable amount of semantically annotated documents. Facing this bootstrapping paradox requires an incremental process of annotation-acquisition-annotation, whereby domain-specific knowledge is acquired from linguistically-annotated texts and then projected back onto texts for extra linguistic information to be annotated and further knowledge layers to be extracted. The presented methodology is a first step in the direction of a full "virtuous" circle where the semantic annotation platform and the evolving ontology interact in symbiosis. As a case study we have chosen the semantic annotation of product catalogues. We propose a hybrid approach, combining pattern matching techniques to exploit the regular structure of product descriptions in catalogues, and Natural Language Processing techniques which are resorted to analyze natural language descriptions. The semantic annotation involves the access to the ontology, semi-automatically bootstrapped with an ontology learning tool from annotated collections of catalogues.}, KEYWORDS = {Information Extraction, Information Retrieval, Ontologies, Tools, Systems}, PAGES = {2079-2085}, URL = {http://www.lrec-conf.org/proceedings/lrec2008/}, PUBLISHER = {European Language Resources Association (ELRA)-Evaluations and Language resources Distribution Agency (ELDA) (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 = {2008}, BOOKTITLE = {LREC 2008, Sixth International Conference on Language Resources and Evaluation}, EDITOR = {Calzolari, N. and Choukri, K. and Maegaard, B. and Mariani, J. and Odjik, J. and Piperidis, S. and Tapias, D.}, } @INPROCEEDINGS{GIOVANNETTI_2007_INPROCEEDINGS_GMMB_84690, AUTHOR = {Giovannetti, E. and Marchi, S. and Montemagni, S. and Bartolini, R.}, TITLE = {Ontology-based Semantic Annotation of Product Catalogues}, YEAR = {2007}, ABSTRACT = {This paper describes a methodology for the semantic annotation of product catalogues. We propose a hybrid approach, combining pattern matching techniques to exploit the regular structure of product descriptions in catalogues, and Natural Language Processing techniques which are resorted to analyze natural language descriptions. It also includes the access to an application ontology, semi-automatically bootstrapped from collections of catalogues with an ontology learning tool, which is used to drive the semantic annotation process.}, KEYWORDS = {Semantic Annotation of texts, Ontology Learning, Information Extraction for e-commerce}, PAGES = {235-239}, URL = {https://publications.cnr.it/doc/84690}, CONFERENCE_NAME = {Recent Advances in Natural Language Processing (RANLP-2007)}, CONFERENCE_PLACE = {Borovets}, CONFERENCE_DATE = {27-29 settembre 2007}, BOOKTITLE = {Proceedings of the International Conference "Recent Advances in Natural Language Processing"}, } @TECHREPORT{AITMOKHTAR_2007_TECHREPORT_ABBDGGMSS_157418, AUTHOR = {Ait Mokhtar, S. and Barker, E. and Brunelli, R. and Demetriou, G. and Gaizauskas, R. and Giovannetti, E. and Montemagni, S. and Sándor, A. and Sun, H.}, TITLE = {Semantic Annotation Services for Virtual Information and Knowledge Environments}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157418}, } @TECHREPORT{BOUQUET_2007_TECHREPORT_BSMGSNSBCJ_157419, AUTHOR = {Bouquet, P. and Stoermer, H. and Montemagni, S. and Giovannetti, E. and Semeraro, G. and Niederee, C. and Stecher, R. and Brunelli, R. and Chanod, J. P. and Jacquin, T.}, TITLE = {Semantic Representation and Management Report}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157419}, } @TECHREPORT{DELLORLETTA_2007_TECHREPORT_DFGLMTP_157412, AUTHOR = {Dell'Orletta, F. and Federico, M. and Giovannetti, E. and Lenci, A. and Marchi, S. and Trabucco, A. and Pirrelli, V.}, TITLE = {Segmentazione di un Testo Italiano in Token}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157412}, } @TECHREPORT{DELLORLETTA_2007_TECHREPORT_DFGLMTP_157413, AUTHOR = {Dell'Orletta, F. and Federico, M. and Giovannetti, E. and Lenci, A. and Marchi, S. and Trabucco, A. and Pirrelli, V.}, TITLE = {Language Recognition Tool, Specifiche di Implementazione}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157413}, } @TECHREPORT{DELLORLETTA_2007_TECHREPORT_DFGLMTP_157414, AUTHOR = {Dell'Orletta, F. and Federico, M. and Giovannetti, E. and Lenci, A. and Marchi, S. and Trabucco, A. and Pirrelli, V.}, TITLE = {Analisi Morfosintattica per l'Italiano}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157414}, } @TECHREPORT{DELLORLETTA_2007_TECHREPORT_DFGLMTP_157415, AUTHOR = {Dell'Orletta, F. and Federico, M. and Giovannetti, E. and Lenci, A. and Marchi, S. and Trabucco, A. and Pirrelli, V.}, TITLE = {Specifiche di Chunking per l'Italiano}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157415}, } @TECHREPORT{DELLORLETTA_2007_TECHREPORT_DFGLMTP_157416, AUTHOR = {Dell'Orletta, F. and Federico, M. and Giovannetti, E. and Lenci, A. and Marchi, S. and Trabucco, A. and Pirrelli, V.}, TITLE = {Specifiche di Named Entity Recognition per l'Italiano}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157416}, } @TECHREPORT{DELLORLETTA_2007_TECHREPORT_DFGLMTP_157417, AUTHOR = {Dell'Orletta, F. and Federico, M. and Giovannetti, E. and Lenci, A. and Marchi, S. and Trabucco, A. and Pirrelli, V.}, TITLE = {Segmentazione di un Testo Inglese in Token}, YEAR = {2007}, URL = {https://publications.cnr.it/doc/157417}, } @INPROCEEDINGS{BARTOLINI_2006_INPROCEEDINGS_BCGLMPRS_84608, AUTHOR = {Bartolini, R. and Caracciolo, C. and Giovannetti, E. and Lenci, A. and Marchi, S. and Pirrelli, V. and Renso, C. and Spinsanti, L.}, TITLE = {Creation and Use of Lexicons and Ontologies for NL Interfaces to Databases}, YEAR = {2006}, URL = {https://publications.cnr.it/doc/84608}, CONFERENCE_NAME = {LREC 2006: 5th International Conference on Language Resources and Evaluation (LREC)}, CONFERENCE_PLACE = {Genova}, CONFERENCE_DATE = {2006}, } @INPROCEEDINGS{BARTOLINI_2006_INPROCEEDINGS_BCGLMPRS_91313, AUTHOR = {Bartolini, R. and Caracciolo, C. and Giovannetti, E. and Lenci, A. and Marchi, S. and Pirrelli, V. and Renso, C. and Spinsanti, L.}, TITLE = {Creation and use of lexicons and ontologies for natural language interface to databases}, YEAR = {2006}, ABSTRACT = {In this paper we present an original approach to natural language query interpretation which has been implemented within the FuLL (Fuzzy Logic and Language) Italian project of BC S.r.l. In particular, we discuss here the creation of linguistic and ontological resources, together with the exploitation of existing ones, for natural language-driven database access and retrieval. Both the database and the queries we experiment with are Italian, but the methodology we broach naturally extends to other languages.}, KEYWORDS = {Natual language processing, ontologies, gis, databases}, PAGES = {6}, URL = {https://publications.cnr.it/doc/91313}, CONFERENCE_NAME = {LREC Conference}, CONFERENCE_PLACE = {Genova}, CONFERENCE_DATE = {24-26/05/2006}, BOOKTITLE = {LREC 2006}, } @INPROCEEDINGS{BARTOLINI_2006_INPROCEEDINGS_BGMMABSB_84664, AUTHOR = {Bartolini, R. and Giovannetti, E. and Marchi, S. and Montemagni, S. and Andreatta, C. and Brunelli, R. and Stecher, R. and Bouquet, P.}, TITLE = {Multimedia Information Extraction in Ontology-based Semantic Annotation of Product Catalogues}, YEAR = {2006}, ABSTRACT = {The demand for efficient methods for extracting knowledge from multimedia content has led to a growing research community investigating the convergence of multimedia and knowledge technologies. In this paper we describe a methodology for extracting multimedia information from product catalogues empowered by the synergetic use and extension of a domain ontology. The methodology was implemented in the Trade Fair Advanced Semantic Annotation Pipeline of the VIKE-framework.}, KEYWORDS = {Semantic Web Technologies, ontology creation, ontology extraction, ontology evolution, semantic annotation of multimedia content}, URL = {https://publications.cnr.it/doc/84664}, CONFERENCE_NAME = {SWAP 2006}, CONFERENCE_PLACE = {Pisa}, CONFERENCE_DATE = {18-20 December 2006}, } @INPROCEEDINGS{BARTOLINI_2006_INPROCEEDINGS_BGMMABSNBB_84663, AUTHOR = {Bartolini, R. and Giovannetti, E. and Marchi, S. and Montemagni, S. and Andreatta, C. and Brunelli, R. and Stecher, R. and Niederée, C. and Bouquet, P. and Bortoli, S.}, TITLE = {Ontology Learning in Multimedia Information Extraction from Product Catalogues}, YEAR = {2006}, ABSTRACT = {We propose a methodology for extracting multimedia information from product catalogues empowered by the synergetic use and extension of a domain ontology. The use of domain ontologies in this context additionally opens up innovative ways of catalogue use. The method is characterized by incrementally feeding and exploiting the ontology during an information extraction process, implemented by the semantic annotation of the analysed document, and by providing support for detecting existing similar ontologies to enable reuse of (parts of) them.}, KEYWORDS = {knowledge-drive multimedia analysis, ontology learning, semi-automatic content annotation tools}, URL = {https://publications.cnr.it/doc/84663}, CONFERENCE_NAME = {BOEMIE 2006}, CONFERENCE_PLACE = {Podebrady, Czech Republic}, CONFERENCE_DATE = {6 ottobre 2006}, }