@INPROCEEDINGS{QUOCHI_2022_INPROCEEDINGS_QBKMMPRTZ_472419, AUTHOR = {Quochi, V. and Bellandi, A. and Khan, F. and Mallia, M. and Murano, F. and Piccini, S. and Rigobianco, L. and Tommasi, A. and Zavattari, C.}, TITLE = {From Inscriptions to Lexica and Back: A Platform for Editing and Linking the Languages of Ancient Italy}, YEAR = {2022}, ABSTRACT = {Available language technology is hardly applicable to scarcely attested ancient languages, yet their digital semantic representation, though challenging, is an asset for the purpose of sharing and preserving existing cultural knowledge. In the context of a project on the languages and cultures of ancient Italy, we took up this challenge. This paper thus describes the development of a user friendly web platform, EpiLexO, for the creation and editing of an integrated system of language resources for ancient fragmentary languages centered on the lexicon, in compliance with current digital humanities and Linked Open Data principles. EpiLexo allows for the editing of lexica with all relevant cross-references: for their linking to their testimonies, as well as to bibliographic information and other (external) resources and common vocabularies. The focus of the current implementation is on the languages of ancient Italy, in particular Oscan, Faliscan, Celtic and Venetic; however, the technological solutions are designed to be general enough to be potentially applicable to different contexts and scenarios.}, KEYWORDS = {Digital Epigraphy, Restsprachen, Lexicon Editing and Linking, tools for DH}, PAGES = {59-67}, URL = {https://aclanthology.org/2022.lt4hala-1.0/}, PUBLISHER = {European language resources association (ELRA) (Paris, FRA)}, ISBN = {979-10-95546-78-8}, CONFERENCE_NAME = {Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2022)}, CONFERENCE_PLACE = {Marseille, France}, CONFERENCE_DATE = {25/06/2022}, BOOKTITLE = {Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2022)}, EDITOR = {Sprugnoli, R. and Passarotti, M.}, } @INPROCEEDINGS{MARINETTI_2022_INPROCEEDINGS_MMQBBDPRSZMM_479194, AUTHOR = {Marinetti, A. and Murano, F. and Quochi, V. and Ballerini, M. and Boschetti, F. and Del Grosso, A. M. and Piccini, S. and Rigobianco, L. and Solinas, P. and Zinzi, M. and Mallia, M. and Middei, E.}, TITLE = {Challenges in Encoding Fragmentary Attested Languages}, YEAR = {2022}, ABSTRACT = {The ItAnt project investigates the langages of ancient Italy, whose only attestation consist in epigraphic evidence, focusing on Venetic, Oscan, Faliscan and Celtic languages. For this purpose, the project combines the traditional method proper to historical linguistics with the setting up of digital technologies, developing computational tools specifically designes to create a digital set of interrelated resources.}, KEYWORDS = {digital epigraphy, eLexicography, Linguistic Linked Open Data, Text Encoding}, URL = {https://ciegl2022.sciencesconf.org/resource/page/id/30}, CONFERENCE_NAME = {XVI Congresso Internazionale di Epigrafia greca e latina}, CONFERENCE_PLACE = {Bordeaux}, CONFERENCE_DATE = {29 agosto-settembre 2022}, } @INPROCEEDINGS{MARINETTI_2021_INPROCEEDINGS_MMQBBDPRS_461529, AUTHOR = {Marinetti, A. and Murano, F. and Quochi, V. and Ballerini, M. and Boschetti, F. and Del Grosso, A. M. and Piccini, S. and Rigobianco, L. and Solinas, P.}, TITLE = {Languages and Cultures of Ancient Italy. Historical Linguistics and Digital Models}, YEAR = {2021}, ABSTRACT = {The abstract accompanies a poster presenting an overview of the project "Languages and cultures of Ancient Italy", which had just started. The project brings together competences from Historical Linguistics, Computational Lexicography and Digital Humanities. The main objective of the project is to investigate the cultures of ancient Italy on the basis of theirlinguistic documentation (7th - 1stc. B.C.) by means of digital tools specifically tailored for their peculiarities.}, KEYWORDS = {digital epigraphy, computational lexicons, text-lexicon linking, restsprachen, digital models, digital humanities}, PAGES = {528-532}, URL = {https://aiucd2021.labcd.unipi.it/en/book-of-abstracts-conference/}, CONFERENCE_NAME = {10th National Conference of Associazione per l'Informatica Umanistica e la Cultura Digitale}, CONFERENCE_PLACE = {Pisa (Virtuale)}, CONFERENCE_DATE = {19-22 gennaio 2021}, } @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}, } @MISC{DELGROSSO_2020_MISC_DPCDFG_484385, AUTHOR = {Del Grosso, A. M. and Piccini, S. and Cosenza, G. and D'Ottavi, G. and Fadda, E. and Gambarara, D.}, TITLE = {Saussure General Linguistics Project: Beyond the Course. A Knowledge Site for Rethinking Saussure's General Linguistics}, YEAR = {2020}, ABSTRACT = {The project is primarily committed to establish a standard scholarly edition of Saussure's General Linguistics related texts, making use of a consistent philological methodology, i.e. aware of the profoundly different textualities of the available sources, that is: autograph unfinished notes for a book, didactic materials (students' notes and Saussure's), and an edited volume.}, KEYWORDS = {Digital Humaniteis, Digital Scholarly Edition, Saussure's manuscripts, Filologia Digitale, Filologia computazionale}, URL = {https://github.com/saussure-team/general-linguistics-project}, } @INPROCEEDINGS{DELGROSSO_2019_INPROCEEDINGS_DP_430371, AUTHOR = {Del Grosso, A. M. and Piccini, S.}, TITLE = {Fixing the Movements of Thought in Text and Terminology: the Effectiveness of Scholarly Digital Tools on Saussure's Writings}, YEAR = {2019}, ABSTRACT = {The aim of this contribution is to present and discuss some recent activities, carried out by the Institute of Computational Linguistics (CNR - Pisa), devoted to representing in an explicit and formal way the diachronic evolution of concepts and terms occurring in Saussure's manuscripts. In the first part of the presentation, we will briefly outline some theoretical aspects concerning the diachronic standpoint in terminology and the "best practices" to be followed when modelling (diachronic) terminological resources. Then, some examples of terminological evolution will be provided, taken from the electronic lexicon Simple_FdS, built within the PRIN project "Per un'edizione digitale dei manoscritti di Ferdinand de Saussure" (2008-2011), based on the Generative Lexicon theory elaborated by Pustejovsky (1995). Terminological data will be shown in LexO, a Web-based and collaborative web editor, which allows for building lexical and terminoontological resources, compliant with the Semantic Web technologies (RDF and OWL). In the second part of the talk, starting from the outcomes of the aforementioned project, we will present the scholarly digital platform aimed at describing and analysing text resources. The encoding approach follows the current de facto standard in representing textual resources, namely the Text Encoding Initiative (TEI) guidelines. In particular, we adopted the tag sets defined in the Module for Transcription of Primary Resources. An example will be illustrated on how describe and visualize the process of writing in Saussure's manuscripts. The example was implemented exploiting the Omega framework as well as the Edition Visualization Technology (EVT). In such a way, scholars have at their disposal a powerful tool for searching additions, deletions, substitutions, retracings, different hands, transpositions, marginal and interlinear notes, and all the other textual phenomena significant to understanding the "Movements of thought" which emerge in the handwritten pages.}, KEYWORDS = {Saussure, Digital Humanities, Digital Scholarly Editing, Digital Philology, Computational Philology}, URL = {https://publications.cnr.it/doc/430371}, CONFERENCE_NAME = {Philosophy of Language and Digital Humanities}, CONFERENCE_PLACE = {Rende (CS)}, CONFERENCE_DATE = {07/05/2019-09/05/2019}, } @MISC{DELGROSSO_2019_MISC_DP_430373, AUTHOR = {Del Grosso, A. M. and Piccini, S.}, TITLE = {Approcci digitali e computazionali allo studio dei documenti manoscritti della tarda latinità: il caso Clavius}, YEAR = {2019}, ABSTRACT = {Introduzione alle digital humanities e alla lessicografia digitale con esempi e riferimenti tratti dal progetto Clavius on the Web.}, KEYWORDS = {digital humanities, digital philology, digital lexicography}, URL = {https://www.dipartimentidieccellenza-dilef.unifi.it/vp-122-calendario-attivita-didattica-marzo-2019.html}, } @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{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.}, } @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{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{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{VALSECCHI_2016_INPROCEEDINGS_VABMP_356355, AUTHOR = {Valsecchi, F. and Abrate, M. and Bacciu, C. and Marchetti, A. and Piccini, S.}, TITLE = {Text Encoder and Annotator: an all-in-one editor for transcribing and annotating manuscripts with RDF}, YEAR = {2016}, ABSTRACT = {In the context of the digitization of manuscripts, transcription and annotation are often distinct, sequential steps. This could lead to difficulties in improving the transcribed text when annotations have already been defined. In order to avoid this, we devised an approach which merges the two steps into the same process. Text Encoder and Annotator (TEA) is a prototype application embracing this concept. TEA is based on a lightweight language syntax which annotates text using Semantic Web technologies. Our approach is currently being developed within the Clavius on the Web project, devoted to studying the manuscripts of Christophorus Clavius, an influential 16th century mathematician and astronomer.}, KEYWORDS = {RDF, Semantic Annotation, Semantic Web}, PAGES = {399-407}, URL = {https://publications.cnr.it/doc/356355}, VOLUME = {9989}, DOI = {10.1007/978-3-319-47602-5_52}, CONFERENCE_NAME = {European Semantic Web Conference 2016}, CONFERENCE_PLACE = {Heraklion, Greece}, CONFERENCE_DATE = {29/05-02/06-2016}, BOOKTITLE = {The Semantic Web}, } @ARTICLE{PICCINI_2015_ARTICLE_P_452104, AUTHOR = {Piccini, S.}, TITLE = {Transimpersonal constructions in Lithuanian: towards the emergence of Split Intransitivity}, YEAR = {2015}, ABSTRACT = {Transimpersonalines konstrukcijos pastaruoju metu yra patraukusios daugelio tyreju, ypac funkcines tipologijos specialistu, demesi, kadangi jos atlieka svarbu vaidmeni formuojantis dalinio intranzityvumo (ang. split intransitivity) modeliams ivairiose kalbose. Straipsnyje naujausiu pasiekimu sviesoje ivertinamos kai kurios lietuviu kalbos konstrukcijos, gramatikose laikomos beasmenemis (,,impersonalinemis"), meginant interpretuoti jas kaip transimpersonalines. Tyrimas atliktas is sinchronines perspektyvos, didziausia demesi skiriant dabartinei bendrinei kalbai, taciau tam tikrais atvejais lyginama ir su senosios lietuviu kalbos ir ypac tarmiu duomenimis. Analize remiasi fizine bukle nusakanciais veiksmazodziais, kurie priklausomai nuo reiksmes gali buti vartojami ivairiose sintaksinese konstrukcijose. Sinchroniname lygmenyje matomas skirtingas siu eksperienciniu veiksmazodziu elgesys gali buti projektuojamas diachronineje perspektyvoje. Taip galima geriau isryskinti ivairius reanalizes proceso, rodancio laipsniska raida dalinio intranzityvumo atsiradimo kryptimi, etapus. Kai kurie veiksmazodziai, atrodo, reanalizes kelyje yra pazenge gana toli, taciau tikrieji dalinio intranzityvumo modeliai dar nesusiformave. Analizuojamuju veiksmazodziu eksperienciniu argumentu subjekto statusas sintakses poziuriu tebelieka problemiskas.}, KEYWORDS = {verbi impersonali, codifica non canonica del soggetto, lituano, intransitività scissa}, PAGES = {19-55}, URL = {http://www.baltistica.lt/index.php/baltistica/article/view/2239/2214}, VOLUME = {50}, DOI = {10.15388/baltistica.50.1.2239}, PUBLISHER = {Mintis; [poi] Vilniaus universiteto leidykla (Vilnius, Lituania)}, ISSN = {0132-6503}, JOURNAL = {Baltistica (Print)}, } @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{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.}, } @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{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}, }