
Pierpaolo Basile
Associate Professor
University of Bari Aldo Moro
Department of Computer Science
Via E.Orabona, 4 - 70126 BARI, Italy
Phone: +39 080 5442301
e-mail: nome.cognome___AT___uniba.it
Ricevimento studenti: martedì 11:30-13:30 stanza 758 - VII piano
Google Scholar Profile
dblp
ORCID profile
Twitter profile
Current Courses
- Sviluppo di Videogiochi - Laurea Triennale in Informatica A.A. 2021/2022
- Metodi Avanzati di Programmazione (Corso B) - Laurea Triennale in Informatica A.A. 2021/2022
Highlights
- The paper "DUKweb, diachronic word representations from the UK Web Archive corpus" is available online on Nature Scientific Data
- Special Issue on "Knowledge Graphs for Search and Recommendation"
- ghigliottin-AI: Solving the Ghigliottina with AI @EVALITA2020
- DIACR-Ita: Diachronic lexical semantics in Italian @EVALITA2020
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 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".
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
- ACL (Association for Computational Linguistics)
- AI*IA (Associazione Italiana per l'Intelligenza Artificiale);
- SIGLEX (the ACL special interest group on the lexicon).
Publications
My updated publications on:
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.
Participation in evaluation campaigns:
- SemEval 2015 Task 13 - Multilingual All-Words Sense Disambiguation and Entity Linking
- SemEval 2015 Task 10 - Sentiment Analysis in Twitter
- EVALITA 2014 - SENTIment POLarity Classification (SENTIPOLC) Task UNIBA at EVALITA 2014-SENTIPOLC Task: Predicting tweet sentiment polarity combining micro-blogging, lexicon and semantic features. The system ranked 1st in the subjectivity and polarity detection tasks. Slides
- SemEval-2014 - Cross-Level Semantic Similarity Task UNIBA: Combining Distributional Semantic Models and Word Sense Disambiguation for Textual Similarity
- ESWC 2014 Semantic Web Evaluation Challenges - Linked Open Data-Enabled Recommender System Challenge - Winner of the Top-N recommendation from binary user feedback Task
- SemEval-2013 - Semantic Textual Similarity Task UNIBA-CORE: Combining Strategies for Semantic Textual Similarity
- SemEval-2012 - Semantic Textual Similarity UNIBA: Distributional Semantics for Textual Similarity
- EVALITA 2011 (Evaluation of NLP and Speech Tools for Italian) 2011 - Super Sense Tagging UNIBA: Super-sense Tagging at EVALITA 2011
- SemEval-2 - Cross-Lingual Lexical Substitution UBA: Using Automatic Translation and Wikipedia for Cross-Lingual Lexical Substitution
- EVALITA 2009 (Evaluation of NLP and Speech Tools for Italian) 2009 - Lexical Substitution Task UNIBA @ EVALITA 2009 - Lexical Substitution Task
- CLEF-2009 - Ad-hoc Robust WSD Task UNIBA-SENSE @ CLEF 2009: Robust WSD task
- CLEF-2008 - Ad-hoc Robust WSD Task UNIBA-SENSE at CLEF 2008: SEmantic N-levels Search Engine
- EVALITA 2007 (Evaluation of NLP and Speech Tools for Italian) 2007 - All-Word Task JIGSAW: An Algorithm for Word Sense Disambiguation
- SemEval-l UNIBA: JIGSAW algorithm for Word Sense DisambiguationEvaluating
Courses
- Metodi Avanzati di Programmazione (Corso B) - Laurea Triennale in Informatica A.A. 2020/2021
- Metodi Avanzati di Programmazione (Corso B) - Laurea Triennale in Informatica A.A. 2019/2020
- Algoritmi e Stutture Dati (Corso B) - Laurea Triennale in Informatica A.A. 2018/2019
- Metodi per il Ritrovamento dell'Informazione - Laurea Triennale in Informatica A.A. 2017/2018
- Metodi per il Ritrovamento dell'Informazione - Laurea Triennale in Informatica A.A. 2016/2017
- Gestione della conoscenza di impresa - Laurea Triennale in Informatica A.A. 2012/2013
- Accesso Intelligente all'Informazione ed Elaborazione del Linguaggio Naturale (modulo B) - Laurea Magistrale in Informatica A.A. 2011/2012
- Gestione della Conoscenza d'Impresa (Brindisi) A.A. 2009/2010