Software and Demo – Literary Computing Lab

Traduco

Traduco is a Web-based, collaborative Computer-Assisted Translation (CAT) tool developed within the “Progetto Traduzione del Talmud Babilonese” which concerns the translation of the Babylonian Talmud into italian. The project is monitored by the Italian Presidency of the Council of Ministers and coordinated by the Union of Italian Jewish Communities and the Italian Rabbinical College. User requirements and specifics have been defined throughout a close collaboration with the project partners afferent to the Union of Italian Jewish Communities and the Italian Rabbinical College (U.C.E.I. – C.R.I.).
Traduco offers a multirole environment: users can either be translators, revisors (that can edit translations done by translators, and keep track of their history), editors (that can arrange the translations in standard formats for desktop publishing software) or administrators.
In addition to the standard components offered by traditional CAT tools, Traduco includes a number of features designed to ease the translation of texts posing specific structural, stylistic, linguistic and hermeneutical challenges.
Traduco integrates state-of the-art algorithms for processing the languages involved in the translation and provides techniques for creating more consistent translations, reducing repetitiveness, and increasing the translation pace.
Traduco is a highly flexible system, that can be easily adapted to be used for the translation of other texts and to deal with other languages.

traduco-screenshot

Related Publications

Bellandi A., Benotto G., Di Segni G., Giovannetti E. (2016). Investigating the Application and Evaluation of Distributional Semantics in the Translation of Humanistic Texts: a Case Study. 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016)

Albanesi, D., Bellandi, A., Benotto, G., Di Segni, G., Giovannetti, E. (2015). When Translation Requires Interpretation: Collaborative Computer–Assisted Translation of Ancient Texts. LaTeCH 2015, 84-88.

Albanesi D., Bellandi A., Benotto G., Giovannetti E. (2015). Translation, Annotation and Knowledge Modelling of the Babylonian Talmud: the Talmud System. In: Proceedings of the Digital Humanities Conference 2015 – DH 2015. Sydney, Australia, 29 June–3 July 2015.

Bellandi A. (2015). Towards a Translation Platform as a Bridge Between Ancient and Modern Languages. Part 2: A Research Infrastructure for Translation and Interpretation of Ancient Texts. In A. Bozzi (ed.), Digital Texts, Translations, Lexicons in the Web, Leo Olschki editore, Firenze.

Bellandi, A., Bellusci, A., Giovannetti, E. (2014). Computer Assisted Translation of Ancient Texts: The Babylonian Talmud Case Study. Natural Language Processing and Cognitive Science: Proceedings 2014, 287.

Bellandi, A., Albanesi, D., Bellusci, A., Bozzi, A., Giovannetti, E. (2014). The Talmud System: a Collaborative web Application for the Translation of the Babylonian Talmud Into Italian. In The First Italian Conference on Computational Linguistics CLiC-it 2014 (p. 53).

Greek into Arabic

The project G2A Web App is aimed at achieving this ambitious target through an architecture based on interconnected modules. In other words, the system works with a nucleus of components for the treatment of both text files and digital image files, which form the core of the system. According to the specific needs, from time to time a number of programs are added both for the management of images (enhancement, segmentation, pattern recognition, etc.) and of text (natural language processing, information extraction, data mining, electronic editing, ecc.).

Demo

Here you can find the demo.

Related Publications

Bozzi A. (2015). Greek Into Arabic, a Research Infrastructure Based on Computational Modules to Annotate and Query Historical and Philosophical Digital Texts. Part I. Methodological aspects. In A. Bozzi (ed.), Digital Texts, Translations, Lexicons in the Web, Leo Olschki editore, Firenze.

Marchi S. (2015). Greek Into Arabic, a Research Infrastructure Based on Computational Modules to Annotate and Query Historical and Philosophical Digital Texts. Part II: System Components and Features. In A. Bozzi (ed.), Digital Texts, Translations, Lexicons in the Web, Leo Olschki editore, Firenze.

Del Grosso, A. M. and Nahli, O. (2014). Towards a flexible open-source software library for multi-layered scholarly textual studies – An Arabic use-case dealing with semi-automatic language processing. In proceedings of the 3th International edition of Colloquium on Information Science and Technology IEEE conference (CIST), 20-22 ottobre 2014, Tetuan.

Del Grosso, A. M. (2013). Indexing techniques and variant readings management. In Studia graeco-arabica vol.3, Published by ERC Greek into Arabic Philosophical Concepts and Linguistic Bridges European Research Council Advanced Grant 249431, C. D’Ancona (a cura di), Pacini Editore, Pisa 2013, pp. 209-230. ISSN 2239-012X.

Nahli O., Giovannetti, E. (2013). Computational contributions for Arabic language processing. In Studia Graeco-Arabica 3, Pacini Editore, Pisa.

Saussure

For the PRIN 2008 project “For a digital edition of Ferdinand de Saussure’s manuscripts” a system for the parallel visualization of facsimile and text content of the manuscripts has been developed. The system, accessible from the Web, also displays the philological and editorial notes on the text and allows users to perform multilingual searches.

Demo

Here you can find a demo

One of the aim of the project was the creation of an electronic thesaurus-lexicon of Saussure’s linguistic terminology. Such a lexicon, based on a multidimensional structuring of the domain specific concepts and that offers a highly structured, rich and explicit semantic representation, allows a scholar to browse and query the lexical data – be it a semantic relation, a semantic feature, a lexical unit, or any combination. The different typologies of queries enable to acquire a deeper understanding of the componential and relational nature of meaning.

Demo

Here you can find a demo

Related Publications

Pesini, L., Del Grosso, A.M., Bozzi, A. 2016. Un’applicazione web per l’edizione elettronica dei manoscritti. CILPR 2013, 239-254.

Piccini, S., Giovannetti, E., Ruimy, N., Bellandi A. 2016. Le lexique électronique de la terminologie de Ferdinand de Saussure: une première. In XXVII Congrès international de linguistique et de philologie romanes, Nancy.

Del Grosso, A. M., Marchi, S., Murano, F., and Pesini, L. 2014. A collaborative tool for philological research: experiments on Ferdinand de Saussure’s manuscripts. In proceedings of revised papers of the 2nd Annual Conference of the Associazione per l’Informatica Umanistica e la Cultura Digitale, M. Agosti, F. Tomasi (eds), CLEUP, Padova, 2014, pp. 163-175. ISBN: 9788867872602.

Del Grosso, A. M., and Marchi, S. 2013. Una applicazione Web per la filologia computazionale. Un esperimento su alcuni scritti autografi di Ferdinand de Saussure. In Guida per un’edizione digitale dei manoscritti di Ferdinand de Saussure, D. Gambarara e M.P. Marchese (a cura di), Edizioni Dell’Orso, Alessandria, pp. 131-157. ISBN: 978-88-6274-478-2.

Piccini, S., Ruimy, N., Giovannetti, E., and Bellandi, A. 2013. Lessicografia Computazionale e Terminologia Saussuriana, Edizioni dell’Orso, Alessandria (Italia), in Guida per un’edizione digitale dei manoscritti di Ferdinand de Saussure.

Querying CLAVIUS

In the context of the project “Clavius on the Web” a diachronic termino-ontological resource, named CLAVIUS, has been developed, aimed at representing the evolution of astronomical concepts and theories from antiquity until the dawn of the modern age. The resource was built by means of existing tools allowing the scholars to formalize knowledge even though they are not familiar with the models and the languages underlying the representation. More specifically, Protégé , a free open-source ontology editor, which supports OWL (and OWL 2) and Chronos, a plug-in for Protégé to manage temporal aspect, were used.
In order to facilitate access for scholars, a demo of a controlled natural language interface was developed to query the ontology. Query templates were created, and each of them is made up of a fixed part that typifies a specific querying model and a variable part that allows the user to select an element of the ontology from the drop-down list. Question templates are processed by the software into SPARQL queries. Queries can be made in controlled natural language by taking into account the lexical level (“What are the relations of a specific term ?”), the ontological level (“What are the relations of a concept denoted by a specific term ?”) or both. The questions themselves could involve diachronic aspects, such as in “what relation exists between two concepts in a specific temporal interval?”.

Demo

Here you can find the demo.

Related Publications

Piccini, S., Abrate, M., Bacciu, C., Bellandi, A., Giovannetti, E., Mancini, L., Marchetti, A. (2016). When Traditional Ontologies are not Enough: Modelling and Visualizing Dynamic Ontologies in Semantic-Based Access to Texts. Digital Humanities 2016 – Book of Abstracts (To appear). 11-16 July 2016. Krakóv (Poland).

Piccini S. 2016. CLAVIUS: verso la modellazione di una risorsa termino-ontologica diacronica del dominio matematico-astronomico del XVII secolo. Atti del XXVI Convegno internazionale Ass.I.Term “Terminologia e organizzazione della conoscenza nella conservazione della memoria digitale” (To appear). 14 – 16 April 2016. Rende (Italy).

LexO

LexO is a web collaborative editor of lexical and termino-ontological resources. LexO is meant to be used mainly by humanists and, thus, hide all the technical complexities related to the adopted formal languages. Being a web application, LexO makes collaborative editing possible: a team of users, each one with his/her own role (lexicographers, domain experts, scholars, etc.), can work on the same resource collaboratively. As a result, resources quickly increase in size and are constantly updated. LexO adheres to international standards for representing lexica and ontologies in the Semantic Web (such as lemon and OWL), so that lexical resources can be shared easily or specific entities can be linked to existing datasets. LexO intends to provide features to link each entity of the resource (being it a form, a term, a concept, etc.) to a text or to a very specific portion of a text, via citational references mechanisms. Conceived to handle historical and ancient lexica and terminologies as well, LexO is flexible and extensible enough to formalize peculiar features of such linguistic resources.

Demo

Here you can find the demo.

Related Publications

- Bellandi, A., Giovannetti, E., and Weingart, A. 2018. Multilingual and Multiword Phenomena in a lemon Old Occitan Medico-Botanical Lexicon. Information, 9(3), 52; doi:10.3390/info9030052.

- Piccini, S., Bellandi, A., and Giovannetti, E. 2018. A Semantic Web Approach to Modelling and Building a Bilingual Chinese-Italian Termino-ontological Resource. To appear in Proceedings of the XVIII EURALEX International Congress, 17-21 July 2018, Ljubljana, Slovenia.

- Bellandi, A., Giovannetti, E., and Piccini, S. 2018. LexO: a Lemon-based Collaborative Editor of Lexical, Terminological and Ontological Resources. To appear in Proceedings of the XVIII EURALEX International Congress, 17-21 July 2018, Ljubljana, Slovenia.

- Bellandi, A., Giovannetti, E., Piccini, S., Weingart, A., 2017. Developing LexO: a Collaborative Editor of Multilingual Lexica and Termino-ontological Resources in the Humanities. In: Francesca Frontini, Larisa Grčić Simeunović, Špela Vintar, Fahad Khan, Artemis Parvisi (eds). Proceedings of the Language, Ontology, Terminology and Knowledge Structures Workshop (LOTKS 2017), Montpellier, 19th September, 2017.