I was born in Nuoro (Sardinia, Italy) in 1983. I got a MA in Translation (Faculty of Foreign Languages, University of Torino) 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 University of Torino, where I joined the Interaction Models (Agents, Language and Expression) Group, now Content-Centered Computing (CCC) group.
I defended my PhD thesis in September 2016.

Since March 2023 I've been a Non-tenured Assistant Professor at the University of Cagliari, where I've been working on a project funded by the National Reform and Resilience Plan (PNRR).

For more details, here is the complete CV.

Research interests

My work primarily focuses on the development of linguistic resources to enhance language understanding and processing. One of my key areas of interest is the study of hate speech and stereotypes in language, but I have also been involved in a wide range of research collaborations regarding the study of task-oriented conversational agents, knowledge-based question answering and multilingualism. Since 2017, I have also been a contributor within the Universal Dependencies community through the development of treebanks and the proposal of unified guidelines for the morphological and syntactic treatment of non-standard linguistic phenomena (mostly learner language and user-generated content).

Publications

For an up-to-date list of publications, see my Google Scholar profile.

Contact

manuela.sanguinetti@unica.it