Curriculum vitae of Cristina Bosco

Education and research

Activities, research topics and projects

The focus of the research is on artificial Intelligence, within computational linguistics and Natural Language Processing (NLP), and it is more precisely oriented to the development and exploitation of linguistic resources, in particular with respect to parsing, machine translation and sentiment analysis.
During PhD, the activity has been devoted to the definition of an annotation format for syntactic trees suitable for Italian language. This format has been applied to a linguistic database for Italian, i.e. the Turin University Treebank (TUT, a project that has been coordinated from the beginning by her as responsible for the area of linguistic resources of her research group. TUT has been extended with various corpora (COSTituzione ITAliana corpus, Wikipedia corpus) achieving the current size of around 3,500 sentences (= 85,000 annotated words).
The treebank, exploited as reference resource for parser training during all the Evalita evaluation campaign for Italian (Evalita 2007, 2009, 2011 and 2014, has been newly released during time in order to improve its quality, and it has been also converted in other annotation formats known in literature (,, for the development of comparison with other resources, also in a cross-linguistic perspective, and for experiments where parser built for other languages and formats are applied. This has determined a meaningful improvement of performance in parsing for Italian while the state-of-the-art, as defined within Evalita 2011 and 2014, has been upgraded to achieve that for English, following dependency-based approaches.
Recently, thanks to a cooperation with the Department of Computer Science of the University of Pisa and the Istituto di Linguistica Computazionale (CNR, Pisa), and a grant from Google, TUT has been introduced in Universal Dependency project promoted by Stanford University (
She coordinated also the development of other corpora, and in particular the parallel treebank for Italian, French and English (ParTUT annotated in TUT format for studying and doing experiments for machine translation, which in 2017 will be introduced like TUT in the Universal Dependency repository.

Another research line refers to the development of resources for sentiment analysis, starting from the SentiTUT corpus (, a collection of social media texts with political content. In this area collocates the development of multilingual corpora among which #mariagepourtous for French, #labuonascuola for Italian and #independencia for Catalan and Spanish, developed in cooperation with colleagues and teams working in French and Spanish universities. In this line, she also plays the role of Principal Investigator in the new project "Hate speech & Social Media: un'analisi del linguaggio dell'odio in Piemonte" (funded by Fondazione CRT).

During the PARLI project (Portale per l’Accesso alle Risorse Linguistiche per l’Italiano, PRIN-2008), where she played the role of national vice-coordinator, within a cooperation with other researchers working in NLP for Italian and with the support of the Associazione Italiana per L’Intelligenza Artificiale, she has developed a portal for accessing all the main resources and system for Italian NLP (

She is the responsible for the University of Turin for the agreement of scientific cooperation (started in 2013 and currently in effect) among the Department of Computer Science of the University of Pisa, the Istituto di Linguistica Computazionale – CNR of Pisa and Department of Computer Science of the University of Turin, as well as for the agreement (Convenzione Quadro) among the Fondazione Bruno Kessler of Trento, the Department of Humanistic Studies of the University of the Western Piedmont, the Department of Enterprise Engineering of the University of Rome Tor Vergata, the Department of Computer Science of the University of Pisa, the Istituto di Linguistica Computazionale – CNR of Pisa and Department of Computer Science of the University of Turin.

She work in the “Content Centered Computing group” ( playing the role of responsible of all the activities related to linguistic resources.

She supervised thesis for PhD, for laurea degree and for master degree

Teaching at university

She participated the the organization of events, among which:

Second Conference for Italian Computational Linguistics - CLIC-It 2015 (as main chair)
Special Session on Emotion and Sentiment in Intelligent Systems and Big Social Data Analysis (SentISData) at IEEE-DSAA 2015 and 2016 (as organizer and chair)
Wokshop Evalita 2014 (as main chair)
Workshop Emotion and Sentiment in Social and Expressive Media (ESSEM) (2013 e 2015 as main chair)
Workshop PARLI (12012)
Workshop Evalita 2011, in convegno AISV (2012)
Workshop Evalita 2009, in coference AI*IA (2009)
Workshop FOMI 2008 (2008)
Workshop Evalita 2007, in conference AI*IA (2007)
Conferenza COGSCI 2005 (2005)

She is in program committee and plays the role of reviewer for journals and conferences, among which:

International Language Resources and Evaluation Conference (LREC)
International Conference on Computational Linguistics (COLING)
workshop Treenbanks and Linguistic Theories (TLT)
Reviewer per IEEE Intelligent System

Current institutional roles

Participation at the committee for teaching computer science in school, which organizes activities for students and teachers of all schools in order to support them in their curricular work.

Other experiences

From July to November 1997, stagist, at the Centre d'Etudes franco-italiennnes (CEFI-CNRS) of the Universitè de Savoie (Chambèry, Francia) for activities related to the development of the web site of the center and research about communication and education in Internet.
Software object-oriented developer at RSI Sistemi of Torino, from January to December 1998

Torino, November the 10th 2016