I was born in Nuoro (Sardinia, Italy) in 1983. I got a MA in Translation (Faculty of Foreign Languages, University of Turin) in 2011 with a thesis on the development of a parallel corpus for Italian, English and French. The corpus has then become the parallel treebank ParTUT. In January 2012, I started my PhD Program in Computer Science at the Department of CS of Turin University, where I joined the Interaction Models (Agents, Language and Expression) Group, now Content Centered Computing group. I defended my PhD thesis in September 2016.
Research
During the PhD program, my research interests mainly focused on the automatic exploitation of linguistic corpora for translation purposes
(both Translation Studies and Machine Translation).
In particular, I've been involved in the development of the multilingual parallel treebank ParTUT
and in the creation of a syntactically-motivated alignment system that exploits information on dependencies provided by this parallel resource.
ParTUT now is also available in Universal Dependencies.
More recently, I've approached other research topics, in particular the ones related to Sentiment Analysis and automatic hate speech detection,
as part of the Hate Speech Monitoring projects coordinated by the Computer Science Department of Turin University.
Publications
2017
- D. Zeman et al., CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, in Proceedings of the CoNLL 2017 Shared Task (to appear), Vancouver, Canada
- M. Sanguinetti, C. Bosco, A.Lavelli, A.Mazzei, F.Tamburini, Annotating Italian Social Media Texts in Universal Dependencies, in Proceedings of the 4th Conference on Dependency Linguistics (DepLing2017) (to appear), Pisa, Italy
2015
- M. Sanguinetti, C. Bosco, ParTUT: the Turin University Parallel Treebank, in R. Basili, C. Bosco, R. Delmonte, A. Moschitti, M. Simi (eds.), Harmonization and Development of Resources and Tools for Italian Natural Language Processing within the PARLI Project, Springer-Verlag
- E. Sulis, M. Lai, M. Vinai, M. Sanguinetti, Exploring Sentiment in Social Media and Official Statistics: a General Framework, in Proceedings of the 2nd Workshop on Emotion and Sentiment in Social and Expressive Media (ESSEM 2015), Istanbul, Turkey
- M. Sanguinetti, Experimenting the use of catenae in Phrase-Based SMT, in Proceedings of the Second Italian Conference of Computational Linguistics (CLiC-it 2015), Trento, Italy
2014
- M. Sanguinetti, C. Bosco, L. Cupi, Exploiting catenae in parallel treebank alignment, in Proceedings of the 9th Conference on Language Resources and Evaluation (LREC2014), Reykjavik, Iceland
- C. Bosco, L. Allisio, V. Mussa, V. Patti, G. Ruffo, M. Sanguinetti, E. Sulis, Detecting Happiness in Italian Tweets: Towards an Evaluation Dataset for Sentiment Analysis in Felicitt`a, in Proceedings of the International Workshop on Emotion, Social Signals, Sentiment and Linked Open Data (ES3LOD 2014), Reykjavik, Iceland
- M. Sanguinetti, C. Bosco, Converting the parallel treebank ParTUT in Universal Stanford Dependencies, in Proceedings of the First Italian COnference of Computational Linguistics (CLiC-it), Pisa, Italy
- M. Sanguinetti, E. Sulis, V. Patti, G. Ruffo, L. Allisio, V. Mussa and C. Bosco, Developing corpora and tools for sentiment analysis: the experience of the University of Turin group, in Proceedings of the First Italian Conference of Computational Linguistics (CLiC-it), Pisa, Italy
- C. Bosco, F. DellOrletta, S. Montemagni, M. Sanguinetti, M. Simi, The Evalita2014 Dependency Parsing Task, in C.Bosco, F. dell'Orletta, S. Montemagni and M. Simi (eds.) Proceedings of Evalita 2014. Evaluation of Natural Language and Speech Tools for Italian, Pisa University Press
- C. Bosco, M. Sanguinetti, Towards a Universal Stanford Dependencies parallel treebank, in Proceedings of the Thirteenth International Workshop on Treebanks and Linguistic Theories (TLT13), Tubingen, Germany
2013
- M. Sanguinetti, C. Bosco, L. Lesmo. Dependency and Constituency in Translation Shift Analysis, In Proceedings of the 2nd Conference on Dependency Linguistics (DepLing2013), Prague, Czech Republic
2012
- C. Bosco, M. Sanguinetti, L. Lesmo, Parallel-TUT: a Multilingual and Multiformat Parallel Treebank, in Proceedings of the 8th Conference on Language Resources and Evaluation (LREC2012), Istanbul, Turkey
- M. Sanguinetti, C. Bosco, Translational Divergences and Their Alignment in a Parallel Multilingual Treebank, in Proceedings of the 11th Workshop on Treebanks and Linguistic Theories (TLT11), Lisbon, Portugal
2011
- M. Sanguinetti, C. Bosco C, Building the Multilingual TUT Parallel Treebank, in Proceedings of the 2nd Workshop on Annotation and Exploitation of Parallel Corpora (AEPC2), Hissar, Bulgaria