array(1) { [0]=> object(Apache_Solr_Document)#24 (3) { ["_documentBoost":protected]=> bool(false) ["_fields":protected]=> array(6) { ["content_id"]=> array(1) { [0]=> string(14) "DIRECTORY_3546" } ["content_title"]=> array(1) { [0]=> string(14) "ROBERTO BASILI" } ["description"]=> array(1) { [0]=> string(15389) "Curriculum vitae Sintetico

Roberto Basili è nato il: 30 Agosto 1964 a Roma.

E’ attualmente Professore Associato presso la Facolta' di Ingegneria della Universita' di Roma, Tor Vergata, dal Maggio 2003, dove svolge attivita' didattica nei corsi di Web Mining e Retrieval, Basi di Dati ed Intelligenza Artificiale. La attività di ricerca svolta dal 1990, è incentrata sui problemi, metodologie e tecnologie dell'Intelligenza Artificiale nelle aree dell'Apprendimento Automatico, Trattamento Automatico delle Lingue (NLP) e nell'ingegneria dei Sistemi di trattamento del linguaggio naturale e di ricerca di informazione distribuita (Distributed & Web Information Retrieval).

E' autore di piu' di 100 pubblicazioni su rivista scientifica ed Atti di Conferenza Internazionale e libri a divulgazione internazionale. E' stato relatore invitato in Conferenze e Workshop Internazionali nell'area dell'apprendimento automatico per il Trattamento Automatico delle Lingue e nella area dell'acquisizione di conoscenza ontologica da collezioni estese di testi, e nel’area dell’Information Retrieval. E' dal 2001 impegnato nei Comitati di Programma ed Organizzatore di Conferenze e Workshop Internazionali. Contribuisce regolarmente inoltre come reviewer nelle maggiori riviste nella sua area di ricerca (tra cui Journal of Artificial Intelligence Research, Applied Artificial Intelligence, ACM Transaction on Speech and Language Processing, Natural Language Engineering) e nel comitato di valutazione delle piu' importanti conferenze scientifichedella sua area di ricerca (ACM SIGIR, ACL, COLING, IJCAI).

 

Attivita' di Ricerca (sintesi)

L'ambito delle sue ricerche recenti e' legato a tre dimensioni principali:

·         Computational Language Learning: Algoritmi per l'apprendimento di conoscenza linguistica nei processi di trattamento automatico delle lingue, con una particolare enfasi sui modelli analitici (vettoriali e statistici) della conoscenza grammaticale e lessicale

·         Ingegneria della conoscenza: acquisizione e ingegnerizzazione di conoscenza ontologica dai testi.

·         L'ingegnerizzazione di modelli per l'Information Retrieval da dati multimediali, l'Information Extraction ed il Question Answering.

 

Responsabilità scientifica in progetti di ricerca internazionali e nazionali,

PRIN 2008: Portale per l'Accesso alle Risorse Linguistiche per l'Italiano (PARLI)

24

Responsabile Unità Tor Vergata

Progetto INSEARCH FP7-SME-2010-1: Supporting SMEs innovation processes through advanced IT Search

24

Responsabile Scientifico

Progetto Prestospace (6 Framework, IST-FP6-2003-507336) (2004-2008)

42

Responsabile Scientifico

DiEM - PON (Programma Operativo Nazionale Ricerca e Competitività 2007-11) PON01_03003 (2011-13)

36

Responsabile Scientifico

DIVINO - Industria 2015 - Made in Italy (Cod. Dom. MI01_00234) (2010-2013)

36

Responsabile Scientifico

Progress-It FILAS 2012 (Protocollo n. FILAS-CR-2011-1089) (2012-2013)

18

Responsabile

NAMIC, IST-HLT (IST-12392) project, dal Febbraio 2000 al Giugno 2004.

36

Junior Investigator

TREVI, Esprit Telematics project n. 21130, dal Novembre 1997 al Dicembre 1999

24

Researcher

ECRAN, Esprit Project n. 2110, Dicembre 1995, Dicembre 1998.

36

Researcher

 

Partecipazione a comitati editoriali di riviste e collane editoriali

Proceedings of the Associations for Computational Linguistics: dal 01/2002  al 11/2012

Proceedings of International Conference on COmputational LINGuistics (COLING): dal 01/2002 al 11/2012

Proceedings of the ACM SIG on Information Retrieval (SIGIR): dal 01/2007 al 11/2012

Incarichi di insegnamento o ricerca presso atenei e istituti di ricerca di alta qualificazione

Co-leader of the John Hopkins Summer Workshop 2003 on "Semantic Analysis Over Sparse Data" dal 11/2002 al 11/2003

Collaborazioni ed Incarichi in accademie di prestigio nel settore di ricerca Conseguimento di premi e riconoscimenti per l'attività scientifica

 

Risultati ottenuti nel trasferimento tecnologico.

Membro fondatore di REVEAL s.r.l., spin-off accademico con partecipazione al 10% della Università di Roma, Tor Vergata, costituita a Dicembre 2012. L’oggetto societario è la progettazione, sviluppo e gestione di processi di text mining avanzato, basati su tecniche quantitative di acquisizione e rappresentazione della conoscenza lessicale per il Semantic Search, l'Information Extraction e la analisi delle opinioni nel Web.

Progetti Industriali Finanziati a livello Internazionale o Nazionale.

Birthday: 30 August 1964 in Rome, Italy.

Current Status: Associate Professor at the Faculty of Engineering, University of Roma, Tor Vergata, since May 2003.

Teaching: Web Mining and Retrieval, Database Systems and Artificial Intelligence.

Research started in 1990 focuses on problems, methodologies and technologies of Artificial Intelligence, in the area of Knowledge Representation, Machine Learning and Natural Language Processing, Engineering of Natural Language Processing Systems and multimedia Information Retrieval.

He is author of more than 100 publications on international journals, proceedings of international Conferences and Workshops. He has been invited speakers in several Workshops and Conferences in the area of Machine Learning for NLP and corpus-driven ontology learning.

He has been member of the Programm and Organizing Committee of more than 20 International Conferences and Workshops. He acts regularly as a reviewer for the most important journals of his research area (among others, Journal of Artificial Intelligence Research, Applied Artificial Intelligence, ACM Transaction on Speech and Language Processing, Natural Language Engineering) as well as in the Reviewing Committee of the most important International Conferences with a yearly schedule (SIGIR, ACL, COLING and IJCAI).

 

Academic Activities

·         Researcher at the Faculty of Engineering, University of Roma, Tor Vergata, from December 1994 to April 2003.

·         Member of the Steering Committee of the Italian Association for Artificial Intelligence ("Associazione Italiana per l'Intelligenza Artificiale"), AI*IA since 2005.

·         Member of ECONA Network (University Network for Research on Cognitive Processing in Artificial and Human Systems) (Centro Interuniversitario di ricerca sull'Elaborazione Cognitiva in Sistemi Naturali ed Artificiali) since 1996.

·         Member and Technical Laboratory Responsible of the Artificial Intelligence and Natural Language Processing research group at the Department of Enterprise Engineering (formerly, DISP Dipartimento di Informatica, Sistemi e Produzione) of the University of Roma, Tor Vergata.

 

Research Activities (a synthesis)

The research has been carried out along the following major lines of study:

·         Computational Natural Language Learning: Algorithms for machine learning and automatic acquisition of linguistic knowledge from raw sources, with a specific emphasis on NLP tasks and resources. Different paradigms have been explored (ranging from logical to neural or probabilistic models) for different complex tasks, like neurofuzzy recogntion of patterns and characters, rule induction and statistical decision making. Major results have been obtained in hybrid inductive models (integrating logical and probabilistic inference) for the acquisition of lexical, grammatical and semantic knowledge. Application to ontology acquisition from texts as concept lattices has been also proposed and tested.

·         The engineering of robust and large scale systems for intelligent text processing in Multimedia Information Retrieval, Information Extraction and Question Answering. This research has progressed along three main directions. Engineering of large scale NLP systems, robust parsing of Natural Languages and evaluation of NLP application. Modular approaches in the engineering of NLP systems have been proposed and tested experimentally on large scale resources in different languages. The critical problems of interoperability and logical complexity of these systems have inspired several original solutions in terms of object-oriented design and architectures as well as efficient algorithms for the solution of specific tasks at different linguistic levels (syntax and semantics). Robust parsing has been approached in terms of a modular and lexicalized approach for two languages (Italian and English). Several parser (SSA and CHAOS) have been fully designed and engineered for English and Italian. Finally, applications like Information rtrieval and Information Extraction have been studied with a specific light on performance evaluation. The specific nature of these linguistic tasks does not allow the application of traditional analytical methods of software engineering. Results of the research in this area refer to original metics for accuracy measurement (information gain and parsing robustness) and on the modeling and devlopment of large scale resources for linguistic benchmarking.

 

Teaching

1999: Invited Teacher (Maitre de Conferences) for Statistical Language Processing, Univeristy of Paris 7.

From 2000: Professor of the Database systems course, Faculty of Engineering, University of Roma Tor Vergata.

From 2004: Professor, Distributed Database, Faculty of Engineering, University of Roma Tor Vergata.

From 2004: Professor, Natural Language Processing, Faculty of Humanities, University of Roma Tor Vergata.

From 2007: Professor, Web Mining and Retrieval, Faculty of Engineering, University of Roma Tor Vergata.

International and National Projects

 

International Projects.

He participated in a large number of national and international research projects as a technical coordinator or senior investigator. The following is synthetic list of the

most representative ones.

·         Prestospace (European Project , 6th Framework, IST-FP6-2003-507336). Focus of the project is on the semantic analysis of multimedia data for archiving and publishing of TV and radio digital archives of the main European TV and audiovisual centers (BBC (UK), RAI (Ita), INA (Fr)).

·         Senior investigator "Semantic Analysis Over Sparse Data" research team of the John Hopkins Summer Workshop, funded by National Science Foundation (NSF), July-August 2003.

·         NAMIC, IST-HLT (IST-12392) project, from February 2000. Tor Vergata technical coordinator. The research on models for automatic authoring of multilingual text collections (press releases).

·         TREVI, Esprit Telematics project n. 21130, from November 1997 to December 1999. Tor Vergata technical coordinator for researches on large scale text processing, for categorization systems modelling, enrichment and press release deliveries.

ECRAN, Esprit Project n. 2110, from December 1995, to December 1998. Tor Vergata technical reference for techniques of lexical-semantic acquisition in Information Extraction scenarios.

 a:0:{}" } ["meta_keywords"]=> array(1) { [0]=> string(1) "," } ["reserved"]=> array(1) { [0]=> string(1) "0" } ["auth_ip"]=> array(1) { [0]=> string(1) "0" } } ["_fieldBoosts":protected]=> array(6) { ["content_id"]=> bool(false) ["content_title"]=> bool(false) ["description"]=> bool(false) ["meta_keywords"]=> bool(false) ["reserved"]=> bool(false) ["auth_ip"]=> bool(false) } } }