My research centres on Natural Language Processing and related technologies. I focus on:
- Neural Language Models
- Semantics
- Multimodality
- Business and Competitive Intelligence
Applications I’m interested include:
- Fact-checking e Fake News Detection
- Affect (Sentiment Analysis, Opinion Mining, Emotion Detection)
- Information Extraction (Term Extraction, Named Entity Recognition, Relation Extraction)
- Domain Adaptation
- Dynamic Annotation of Language Resources
PRIN 2022 PNRR | New Frontiers for a Participatory Criminal Justice Towards the Thresholds of Metaverse
The project delves into the impact of ICT technologies on the decision-making activity of judges and on the conduct of remote processes.
PRIN 2022 | Psychologically-tailored approaches to Debunk Fake News detected automatically by an innovative artificial intelligence approach
The project studies the topic of Fake News recognition and personalized debunking based on psychological and behavioral characteristics of individuals.
FAIR | Future Artificial Intelligence Research
The project aims to contribute to addressing research questions, methodologies, models, technologies, and also ethical and legal rules for building Artificial Intelligence systems. Within the project, the contribution is part of Spoke 1 coordinated by the University of Pisa, specifically in WP1.3 (Human-Centered Lifelong Learning for Complex Data).
Giustizia AGILE | PON 2014-2020
The project aims to enhance the efficiency of judicial offices through technological innovation and organizational support. The actions have focused on implementing advanced IT solutions, promoting efficient organizational practices, disseminating innovations, and facilitating management. The University of Pisa group has focused on information extraction from legal documents and populating a search engine for document consultation.
CLMs4BPO | Conditional Language Models for Business Process Optimization (Scientific Coordinator)
Project funded by the Tuscany Region for the activation of Research Fellowships. The project proposed a tool for the automatic generation of text conditioned by explicit metadata. The implemented solution is based on Generative Artificial Intelligence techniques, specifically using instruction-tuned Large Language Models.
TAILOR | Foundations of Trustworthy AI – Integrating Reasoning, Learning and Optimization (EU-H2020)
TAILOR consortium is committed to demonstrate that research and innovation based on expertise, cooperation, and diversity can achieve the European vision of Human-Centered Trustworthy AI and make Europe the global role-model for responsible AI.
Event Extraction for Fake News Detection
The project is focused on the development of a system for fake news detection by means of a graph-based representation of news events and actors. The project is in collaboration with the Computer Science and Artificial Intelligence Lab of the Massachussets Institute of Technology (CSAIL-MIT)
MUSE - MUltimodal Semantic Extraction
Project funded by Regione Toscana POR FSE 2014-2020 Asse A . The goal of the project is the semantic multimodal analysis of both texts and images by exploiting Natural Language Processing and Computer Vision techniques. The project is in collaboration with the Company BNova s.r.l.
SEM - Sem Il Chattadino
Project funded by Regione Toscana POR CreO Fesr 2014-2020. The goal of the project is the creation of a ChatBot able to provide information about the Public Administration domain. The project brings together the CoLing Lab and the companies ETI$^3$ s.r.l., BNova s.r.l. and Rigel Engineering s.r.l.
UBIMOL - UBIquitous Massive Open Learning
Project funded by Regione Toscana POR FESR 2014 – 2020. UBIMOL aims at developing an E-learning platform enriched with innovative NLP technologies able to offer personalized courses. The project involves the companies M.E.T.A. Srl, 01Sistemi Srl, VIDITRUST Srl, PERSAFE Srl and the research partners ILC-CNR and CoLing Lab (University of Pisa)
Memorie di Guerra
The goal of this project is the application of State-of-the-Art NLP techniques to war memories and historical documents, in order to enhance historical research and to preserve the historical memory of these events. The project involves other research partners like ILC-CNR and University of Siena
SEMPLICE - SEMantic instruments for PubLIC admnistrators and CitizEns
A 2-year project funded by Regione Toscana aimed at the development of NLP-based tools for knowledge management, information extraction and opinion mining for local public administrations. This project brings together University of Pisa and Tuscany Companies like 01S, BNova, Seacom.