Pierpaolo Basile is an Associate Professor at the University of Bari, Italy. His expertise is in Natural Language Processing, in particular, in Semantics. Since 2005, his research has been on methods for understanding natural language. He is also CEO of AI2B (a spin-off of the University of Bari) and co-founder of QuestionCube.
Highlights
- Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA. paper, Hugging Face
- LLaMAntino: LLaMA 2 models for effective text generation in Italian language. paper, Hugging Face
Education
Ph.D. in Computer Science, University of Bari Aldo Moro
Ph.D. in Computer Science. Thesis title :“Word Sense Disambiguation and Intelligent Information Access”, Advisor: Professor Giovanni Semeraro.
Master degree in Computer Science
Master degree in Computer Science. Thesis title: “JIGSAW: un algoritmo di disambiguazione diversificato per ogni categoria grammaticale” (JIGSAW: a word sense disambiguation algorithm with different approaches for each part-of-speech), Supervisor: Professor Giovanni Semeraro.
Current courses
- Laboratorio di Informatica (starting A.A. 2024/2025)
- Sviluppo di Videogiochi - Laurea Triennale in Informatica
- Metodi Avanzati di Programmazione (Corso B) - Laurea Triennale in Informatica
- Natural Language Processing - Master in Computer Science
Main Research Interests
Natural Language Processing
- Word Sense Disambiguation and Entity Linking
- Distributional Semantic Models and Compositional Semantics
- Statistical Methods for Natural Language Processing
- Diachronic Analysis of Language
- Sentiment Analysis
Intelligent Information Access
- Natural Language Processing for Information Retrieval
- Information Filtering
- Recommender Systems
- Machine Learning Techniques for Recommender Systems
Short CV
- From December 2019 to December 2021 - Assistant Professor (Ricercatore a Tempo Determinato - B).
- From January 2016 to December 2019 - Assistant Professor (Ricercatore a Tempo Determinato - A) at the University of Bari. Principal investigator of the Future in Research project: “Multilingual Entity Linking”.
- From March 2017 to Aprile 2017 - Visiting researcher at the Alan Turing Institute, UK.
- From July 2013 to January 2016 - Post-doc researcher at the University of Bari. Project: “Compositional Operators in Distributional Semantic Models”.
- From June 2009 to June 2013 - Post-doc researcher at the University of Bari. Project: “Methods and techniques for the semantic indexing of textual documents”.
- May 2009 - Receive the Ph.D. in Computer Science from the University of Bari. Ph.D. thesis title: “Word Sense Disambiguation and Intelligent Information Access”.
- From May 2008 to July 2008 - Internship at the University of Basque Country (IXA research group). Research topic: a combination of unsupervised Word Sense Disambiguation algorithms.
- July 2005 - Receive the degree in Computer Science from the University of Bari. Thesis title: “JIGSAW: a Word Sense Disambiguation algorithm”.
Research Project
- FAIR - Future Artificial Intelligence Research project - Spoke 6 “Symbiotic AI”.
Events Co-organizer
- NL4AI 2020 co-chairs, 4th Workshop on Natural Language for Artificial Intelligence
- Sponsorship chair: Sesta Conferenza Italiana di Linguistica Computazionale (CLiC-it 2019)
- Local co-organizer: Sesta Conferenza Italiana di Linguistica Computazionale (CLiC-it 2019)
- EVALITA 2018, iLISTEN task, the first itaLIan Speech acT labEliNg task at EVALITA18
- EVALITA 2018, ABSITA task, Aspect-based Sentiment Analysis at EVALITA
- EVALITA 2018, NLP4FUN task, Solving language games at EVALITA18
- Workshop on REbooting the COnVErsational Recommender Systems at RecSys 2018
- NL4AI 2018 co-chairs, 2nd Workshop on Natural Language for Artificial Intelligence
- NL4AI 2017 co-chairs, 1st Workshop on Natural Language for Artificial Intelligence
- TDDL 2017 co-chairs, 1st Workshop on Temporal Dynamics in Digital Libraries
- EVALITA 2016 co-chairs, Evaluation of NLP and Speech Tools for Italian
- Third Italian Information Retrieval Workshop - IIR2012 Bari, Italy, January 26-27, 2012
- Intelligent Information Access (IIA) 2008. Cagliari, December 9-11, 2008. Role: local organizer;
- 4th Workshop on Semantic Web Applications and Perspectives (SWAP) 2007. Bari, December 18-20, 2007. Role: local organizer;
- Convegno Italiano di Logica Computazionale (CILC) 2006. Bari, June 26-27, 2006. Role: local organizer.
Associations
- AILC (Associazione Italiana di Linguistica Computazionale): board member and secretary
-
AI*IA (Associazione Italiana per l’Intelligenza Artificiale): board member
Publications
- Google Scholar Profile
- ORCID
- DBLP
- ACM Digital Library
-
ACL Anthology
Tools
- Temporal Random Indexing
- Extending and Information Retrieval System through Time Event Extraction
- An Enhanced Lesk Word Sense Disambiguation algorithm through a Distributional Semantic Model
- META - MultilanguagE Text Analyzer is a tool for text analysis which implements some NLP functionalities. It provides the tools for semantic indexing and exploits WordNet as knowledge source in Word Sense Disambiguation processing.
- UNIBA: JIGSAW algorithm for Word Sense Disambiguation. JIGSAW is available on github JIGSAW on github
- JIGSAW_hybrid: Word Sense Disambiguation algorithm for Italian
- ITR: ITem Recommender is a content-based item recommender based on a Naïve Bayes text classifier where the user profile contains the probabilistic model (words/synsets + probabilities) of user preferences.