TALP Research Center for Language and Speech Technology and Applications
Natural Language Processing Research Group

Departament de Llenguatges i Sistemes Informàtics.
Universitat Politècnica de Catalunya.

Despatx 213 - Mòdul C6
Campus Nord UPC
C/ Jordi Girona Salgado 1-3
E-08034 Barcelona
Catalonia

Tel:  34-93-4015651
Fax: 34-93-4017014
E-mail:  g.rigau@lsi.upc.es or  g.rigau@talp.upc.es
Home Pages:  http://www.lsi.upc.es/~rigau or  http://www.talp.upc.es/users/rigau

Curriculum Vitae

Under-graduate courses

EDA
TMIA (Curs de Prolog) (GNU Textutils) (Unix for Poets Slides)

Post-graduate courses

46006 Introduction to Natural Language Processing  (Course slides)
46017 Techniques for Natural language Processing (Acquisition of Lexical Knowledge for NLP, Ontologies, Word Sense Disambiguation)
 

I am a member of the Artificial Intelligence Section of my department, and more specifically, I work in the Natural Language Processing Research Group within TALP Research Center for Language and Speech Technology and Applications. I research on the automatic acquisition of lexical knowledge from MRDs and Word Sense Disambiguation. Recently, we participated in SENSEVAL, a Word Sense Disambiguation evaluation exercise (sponsored by ACL SIGLEX). We are now involved in the second edition SENSEVAL-2.

Co-authored with Eneko Agirre, Semi-automatic Methods for WordNet construction tutorial of Global WordNet in Mysore, India 2002.

PhD thesis

      Automatic Acquisition of Lexical Knowledge from MRDs
      German Rigau i Claramunt
      Advisor: Horacio Rodríguez Hontoria.
      PhD Thesis, Departament de Llenguatges i Sistemes Informàtics.
      Universitat Politècnica de Catalunya.
      Barcelona, 1998.

PhD thesis Students

Jordi Atserias  (co-advisor Lluís Padró)
Jordi Daudé  (co-advisor Lluís Padró)
Gerard Escudero  (co-advisor Lluís Màrquez)
Andrés Montoyo  (co-advisor Manuel Palomar)
Toni Tuells

Acquilex I and II


Duration: 3 + 3 years
Funding: European Commission under the Basic Research initiative (BRA-3030 and BRA-7315).
Summary: The goal of the first project was to explore the utility of constructing a multilingual lexical knowledge base from machine-readable versions of conventional dictionaries. The second project extended this goal by exploring the utility of machine readable textual corpora as a source of lexical information not coded in conventional dictionaries, and by adding dictionary publishing partners to exploit the lexical database and corpus extraction software developed by the projects for conventional lexicography. The ACQUILEX II project finished in September 1995. Partners in this project are: University of Cambridge, University of Amsterdam, Instituto di Linguistica Computazionale of CNR, and the cooperation of the NL research groups from UPC and UB.

EuroWordNet: Building a multilingual wordnet with semantic relations between words



Duration: 3 years
Funding: European Union through Language Engineering sector of the Telematics Applications Programme (LE-2 4003).
Summary: This project aims to develop a generic multilingual database with WordNets for several European languages -English, Dutch, Italian and Spanish- with 30,000 senses each one. Those WordNets will be linked through the English WordNet, so each English synonym will be associated with its equivalent in the other languages.
Partners in this project are: University of Amsterdam, University of Sheffield, Instituto di Linguistica Computazionale of CNR,  Lernout & Hauspie and the NL research groups from UPC, UNED and UB.

Wordnet homepage at http://www.cogsci.princeton.edu/~wn/
 

Now you can try our Web Interface to Multilingual  (English, Spanish, Catalan and Basque) WordNet.


EuroWordNet homepage at http://www.illc.uva.nl/EuroWordNet/
 

Now you can try our Web Interface to Multilingual (English, Spanish, Catalan and Basque) EuroWordNet.

Now available the final results of EuroWordNet.

Now the complete mapping between WordNet 1.5 and WordNet 1.6.

Now the complete mapping between WordNet 1.6 and WordNet 1.7.
 
 

• ITEM: Textual Information Retrieval in a multilingual environment using NL Techniques

Duration: 3 years
Funding: CICYT (TIC96-1234-C03-02)
Summary: The project aims to explore how natural language processing techniques can improve state of the art of retrieval systems on full-text and multimedial databases. The project aims to find improvements in methods to retrieve relevant documents and to allow multilingual acces to them.
ITEM is a project developed by our group from Technical University of Catalonia (UPC), toghether with members of the University of Barcelona (UB) Computational Linguistics research group, the NLP group from Basque Country University (EHU), and the NLP research group in the Universidad Nacional de Educación a Distancia (UNED). Researchers from the Jaume I University of Castellón also participate and work in close relationship with us. More information on the ITEM project.

Now you can test our analyzers for unrestricted Spanish and Catalan text.

Now you can test the Cross-Language Information Retrieval System developed by UNED.
 
 

• RILE: Spanish Linguistic Resources Server

Duration: 6 months.
Funding: ATYCA (Culture and Language sector, Technologies and Aplications for the Information Society program). Ministerio de Industria y Energia.
Summary: This project is a pilot test for the development of a Spanish Linguistic Resources Server including some of the linguistic engineering tools developed in ITEM.
This project is developed by our group from Technical University of Catalonia (UPC), toghether with members of the University of Barcelona (UB) Computational Linguistics research group, the NLP research group in the Universidad Nacional de Educación a Distancia (UNED), Sema Group and Observatorio Español de Industrias de la Lengua - Instituto Cervantes.
 
• Catalan WordNet

Duration: 3 years
Funding:CREL (Centre de Referència en Enginyeria Lingüística) recently created by CIRIT.
Summary: This project aims to develop the Catalan WordNet following the framework of EuroWordNet. The Catalan WordNet will be linked through the English WordNet, so each English synonym will be associated with its equivalent in Catalan.
The partner of this project is the NL research group of UB.

 

Wordnet homepage at http://www.cogsci.princeton.edu/~wn/

 

Now you can try our Web Interface to Multilingual  (English, Spanish, Catalan and Basque) WordNet.

EuroWordNet homepage at http://www.illc.uva.nl/EuroWordNet

 
Now the complete mapping between WordNet 1.5 and WordNet 1.6.

Now the complete mapping between WordNet 1.6 and WordNet 1.7.
 
 

Spontaneus-Speech Dialogue System In Limited Domains

Duration: 3 years
Funding: CICYT (TIC98-423-C06)
Summary: This project propose the development of an oral human-machine interface, by way of dialogue, for a semantically limited task (for instance: queries into a database with information regarding ticket reservation, tourist information or first aid care, or similar tasks). The oral interfaces based on dialogue will allow the development of services unavailable today, for accessing information or help or for carrying out transactions over the telephone (alternatively, they may render current services with important performance shortcomings more efficient).
This project is developed by our group from Technical University of Catalonia (UPC), toghether with Computational Linguistics research group of the University of Barcelona (UB), Grupo de Tratamiento del Habla also from the (UPC), the Grupo de Reconocimiento Automático del Habla  from Basque Country University (EHU), the Grupo de Aprendizaje Computacional, Reconocimiento Automático y Traducción del Habla from the Jaume I University of Castellón, the  Grupo de Reconocimiento de Formas e Inteligencia Artificial from the University of Valencia, and the Grupo de Tecnologias de las Comunicaciones from the University of Zaragoza. More information on the project .

• NAMIC: News Agencies Multilingual Information Categorisation


Duration: 2 years.
Funding: European Union through Information Society Technologies programme (IST-1999-12392).
Summary: This project aims to develop and bring to marketable stage advanced technologies of Natural Language Processing for multilingual news customisation and broadcasting throughout distributed services, a major problem for International and National News Agencies (NA) as well as for the spread of Web technologies. Within their own business cases, NAs need to integrate within their own repositories news distributed by other NAs usually in different languages and according to different classification standards. Mismatching is at language level, a different languages are used, as well as at conceptual level, as the organization/storage of news proceeds according to diverging schemes.This project will include the linguistic engineering tools developed in ITEM , RILE and EuroWordNet.
This project is developed by our group from Technical University of Catalonia (UPC), toghether with members of the University of Barcelona (UB) Computational Linguistics research group with the research groups of University of Sheffield, University of Roma Tor Vergata and Vrije Universiteit Brussel, and Itaca, International Press Telecommunications Council, Agenzia ANSA, Agencia EFE and Financial Times.

• HERMES: Electronic Libraries with Multilingual Information Retrieval and Semantic Processing



Duration: 3 years (2001-2003)
Funding: CICYT (TIC2000-0335-C03-02)
Summary: In the HERMES project two applications will be developed which facilitate the retrieval of multilingual textual information. These applications will offer significant improvements over current systems due to the incorporation of techniques taken from the field of linguistic engineering. The improvements will be seen interms of the relevance of the obtained results and also in the analysis and presentation of the selected information. The first application will be a system that deals with requests for information contained in a multilingual (Basque, Catalan, English and Spanish) digital news archive. The second application will be a Web-based multilingual search system of online news (e.g., Web-based newspapers).
HERMES is a project developed by our group from Technical University of Catalonia (UPC), toghether with members of the University of Barcelona (UB) Computational Linguistics research group, the NLP group from Basque Country University (EHU), and the NLP research group in the Universidad Nacional de Educación a Distancia (UNED).
 

• MEANING: Developing Multilingual Web-scale Language Technologies



Duration: 3 years (2002-2005).
Funding: European Union through Information Society Technologies programme (IST-2001-34460).
Summary: MEANING will be concerned with automatically collecting and analysing language data from the WWW on a large scale, and building more comprehensive multilingual lexical knowledge bases to support improved word sense disambiguation (WSD).
Current web access applications are based on words; MEANING will open the way for access to the Multilingual Web based on concepts, providing applications with capabilities that significantly exceed those currently available. MEANING will facilitate development of concept-based open domain Internet applications (such as Question/Answering, Cross Lingual Information Retrieval, Summarisation, Text Categorisation, Event Tracking, Information Extraction, Machine Translation, etc.). Furthermore, MEANING will supply a common conceptual structure to Internet documents, thus facilitating knowledge management of web content.
This project will include the linguistic engineering tools developed in ITEM , RILE and EuroWordNet and NAMIC.
This project is developed by our group from Technical University of Catalonia (UPC) with the research groups of ITC-IRST, Ixa Group at EHU, University of Sussex, Irion Technologies B.V. and  Reuters Limited.

• Ageno A., Castellón I., Martí M.A., Ribas F., Rigau G., Rodriguez H., Taulé M. and Verdejo M.F.,SEISD: An environment for extraction of Semantic Information from on-line dictionaries. Proceedings of the 3rd Conference on Applied Natural Language Processing ANLP'92. Trento, Italy, 1992.
• Rigau G., An experiment on Automatic Semantic Tagging of Dictionary Senses. WorkShop The Future of Dictionary. Aix-les-Bains, France, 1994. Also as a research report LSI-95-31-R. Dept. de Llenguatges i Sistemes Informàtics. UPC. Barcelona. June 1995.
• Ageno A., Ribas F., Rigau G., Rodríguez H. and Samiotou A., TGE: Tlinks Generation Enviroment. Proceedings of 15th International Conference on Computational Linguistics, COLING'94. Kyoto, Japan, 1994.
• Copestake A., Briscoe E., Vossen P., Ageno A., Castellón I., Ribas F., Rigau G., Rodríguez H. and Samiotou A.,  Acquisition of Lexical Translation Relations from MRDs. Machine Translation: Special Issue on the lexicon, 9:3,33-69, 1995.
• Rigau G. and Agirre E., Disambiguating bilingual nominal entries against WordNet. Proceedings of workshop "The Computational Lexicon". Ed. F. Verdejo. 7th European Summer School in Logic, Language and Information, ESSLLI'95. Barcelona, Spain, 1995.
• Agirre E. and Rigau G., A Proposal for Word Sense Disambiguation using Conceptual Distance. Proceedings of the International Conference "Recent Advances in Natural Language Processing" RANLP'95, Tzigov Chark, Bulgaria, 1995. Also in Recent Advances in Natural Language Processing. Eds. Mitkov R. and Nicolov N., Vol. 136 of the series Current Issues in Linguistic Theory. Jon Benjamins Publishing Company. Amsterdam, The Netherlands. 1997.
• Rigau G., Rodríguez H. and Turmo J., Automatically extracting Translation Links using a wide coverage semantic taxonomy. Proceedings 15th International Conference AI'95. Montpellier, France. 1995.
• Agirre E. and Rigau G., Word Sense Disambiguation using Conceptual Density. Proceedings of 15th International Conference on Computational Linguistics, COLING'96. Copenhagen, Denmark, 1996.
• Atserias J., Climent S., Farreres J., Rigau G. and Rodríguez H., Combining Multiple Methods for the Automatic Construction of Multilingual WordNets. Proceedings of the International Conference "Recent Advances on Natural Language Processing" RANLP'97. Tzigov Chark, Bulgaria, 1997.
• Rigau G., Atserias J. and Agirre E., Combining Unsupervised Lexical Knowledge Methods for Word Sense Disambiguation. Proceedings of joint 35th Annual Meeting of the Association for Computational Linguistics and  8th Conference of the European Chapter of the Association for Computational Linguistics ACL/EACL'97. Madrid, Spain, 1997.
• Benítez L., Cervell S., Escudero G., López M., Rigau G. and Taulé M., Methods and Tools for Building the Catalan WordNet. Proceedings of the ELRA Workshop on Language Resources for European Minority Languages, First International Conference on Language Resources & Evaluation, Granada, Spain. 1998.
• Rigau G., Rodríguez H. and Agirre E., Building Accurate Semantic Taxonomies from Monolingual MRDs. Proceedings of the 17th International Conference on Computational Linguistics and 36th Annual Meeting of the Association for Computational Linguistics COLING-ACL'98. Montreal, Canada. 1998.
• Farreres X., Rigau G. and Rodríguez H., Using WordNet for Building WordNets. Proceedings of COLING-ACL Workshop "Usage of WordNet in Natural Language Processing Systems". Montreal, Canada. 1998.
• Vossen P., Bloksna L., Alonge A., Marinai E., Peters C., Castellón I., Martí M.A. and Rigau G., Compatibility in Interpretation of Relation in EuroWordNet. Computers and the Humanities, Double Special Issue on EuroWordNet. Eds. Nancy Ide and Dan Greenstein. 32:2,3, 153-184, 1998. Also in EUROWORDNET A Multilingual Database with Lexical Semantic Networks ed. Piek Vossen. Kluwer Academic Publishers. Dordrecht, The Netherlands. 1998.
• Daudé J., Padró L. and Rigau G., Mapping Multilingual Hierarchies using Relaxation Labelling, Proceedings of Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC'99). Maryland, United States, 1999.
• Atserias J., Castellón I., Civit M. and Rigau G., Using a Diathesis Model for Semantic Parsing, 1th Venezia per il Trattamento Automatico delle Lingue (VExTAL'99). Venice, Italy, 1999.
• Agirre E., Atserias J., Padró L. and Rigau G., Combining Supervised and Unsupervised Lexical Knowledge Methods for Word Sense Disambiguation Computers and the Humanities, Special Double Issue on SensEval. Eds. Martha Palmer and Adam Kilgarriff. 34:1,2, 2000.
• Atserias J., Castellón I., Civit M. and Rigau G., Semantic Analysis based on Verbal Subcategorization. Proceedings of the Conference on Intelligent Text Processing and Computational Linguistics (Cicling'2000), Mexico. 2000.
• Escudero G., Màrquez L. and Rigau G., Boosting Applied to Word Sense Disambiguation. Proceedings of the 11th European Conference on Machine Learning, ECML 2000. Barcelona, Spain. 2000. Lecture Notes in Artificial Intelligence 1810. R. L. de Mántaras and E. Plaza (Eds.). Springer Verlag 2000. Also as a research report LSI-00-03-R. Dept. de Llenguatges i Sistemes Informàtics. UPC. Barcelona. 2000.
• Escudero G., Màrquez L. and Rigau G., Naive Bayes and Exemplar-Based approaches to Word Sense Disambiguation Revisited.  Proceedings of the 14th European Conference on Artificial Intelligence, ECAI-2000. Berlin, Germany. 2000. Also as a research report LSI-00-05-R. Dept. de Llenguatges i Sistemes Informàtics. UPC. Barcelona. 2000.
• Escudero G., Màrquez L. and Rigau G., A Comparison between Supervised Learning Algorithms for Word Sense Disambiguation. Proceedings of Fourth Computational Natural Language Learning Workshop (CoNLL-2000). Lisbon. Portugal. 2000.
• Escudero G., Màrquez L. and Rigau G., An Empirical Study of the Domain Dependence of Supervised Word Sense Disambiguation Systems. Proceedings of Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC'00). Hong Kong, China. 2000. Derived from On the Portability and Tuning of Supervised Word Sense Disambiguation Systems. Research Report LSI-00-30-R. Dept. de Llenguatges i Sistemes Informàtics, UPC. 2000.
• Daudé J., Padró L. and Rigau G., Mapping WordNets using Structural Information, Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics ACL'00. Hong Kong, China. 2000.
• Daudé J., Padró L. and Rigau G., A Complete WN1.5 to WN1.6 Mapping, Proceedings of NAACL Workshop "WordNet and Other Lexical Resources: Applications, Extensions and Customizations". Pittsburg, PA, United States, 2001.
• Montoyo A., Palomar M. and Rigau G., WordNet Enrichment with Classification Systems. Proceedings of NAACL Workshop "WordNet and Other Lexical Resources: Applications, Extensions and Customizations". Pittsburg, PA, United States, 2001.
• Montoyo A., Palomar M. and Rigau G., Lexical Enrichment of WordNet with Classification Systems using Specification Marks Method. 6th International Workshop on Applications of Natural Language for Information Systems NLDB'01. Madrid, Spain. 2001. Published in Lecture Notes in Informatics, P-3, German Informatics Society GI-Edition, 2001.
• Basili R., Catizone R., Padró L., Pazienza M.T., Rigau G., Setzer A., Webb N., Wilks Y., Zanzotto F., Multilingual Authoring: the NAMIC Approach. Proceedings of the ACL Workshop "Human Language Technology and Knowledge Management". Toulouse, France. 2001.
• Montoyo A., Palomar M. and Rigau G., Method and Interface for WordNet Enrichment with Classification Systems. Proceedings of 12th International Conference on Database and Expert Systems Applications DEXA-2001. Munich, Germany. 2001. Published in Lecture Notes in Computer Science 2113, Springer-Verlag, 2001.
• Atserias J., Padró L. and Rigau G., Integrating Multiple Knowledge Sources for Robust Semantic Parsing. Proceedings of the International Conference "Recent Advances on Natural Language Processing" RANLP'01. Tzigov Chark, Bulgaria. 2001.
• Montoyo A., Palomar M. and Rigau G., Method for WordNet Enrichment Using WSD, Proceedings of 4th International Conference on Text Speech and Dialogue TSD'2001. Selezná Ruda - Spièák, Czech Republic. 2001. Published in Lecture Notes in Artificial Intelligence 2166, Springer-Verlag, 2001.
• Rigau G., Taulé M. and Fernandez A. and Gonzalo J., Framework and Results for the Spanish SENSEVAL. Proceedings of 2nd International Workshop "Evaluating Word Sense Disambiguation Systems", SENSEVAL-2. Toulouse, France. 2001.
• Escudero G., Màrquez L. and Rigau G. Using LazyBoosting for Word Sense Disambiguation. Proceedings of the 2nd International Workshop "Evaluating Word Sense Disambiguation Systems", SENSEVAL-2. Toulouse, France. 2001.
• Basili R., Catizone R., Padró L., Pazienza M.T., Rigau G., Setzer A., Webb N. and Zanzotto F., Knowledge-Based Multilingual Document Analysis. Proceedings of COLING Workshop "SemaNet'02: Building and Using Semantic Networks" Taipei, Taiwan. 2002.
• Rigau G., Magnini B., Agirre E., Vossen P. and Carroll J., MEANING: A Roadmap to Knowledge Technologies. Proceedings of COLING Workshop "A Roadmap for Computational Linguistics". Taipei, Taiwan. 2002.