CBA 2008
Corpus-Based Approaches to Coreference Resolution in Romance Language


Call for papers CBA2008


Universitat de Barcelona and Universitat Politècnica de Catalunya begin a series of workshops devoted to Corpus-based Approaches to Discourse Analysis – CBA Workshops. We are particularly interested in innovative perspectives on the use and exploitation of corpora in going one step beyond the state of the art. The first workshop in this series, CBA-2008, will focus on “Coreference Resolution in Romance Languages.”

This workshop aims to exploit annotated data in order to make the most of machine learning techniques for coreference resolution. For coreference we understand identifying the full chain of mentions for each entity in the discourse, rather than pairs of antecedent-anaphor. We believe there is a need to bring together linguists and computer scientists, and we invite unpublished contributions which relate to issues of this field with a special emphasis on – though not limited to – Romance languages.

                  • Exploring techniques/strategies for collecting better data in this area
                  • Studies of relevant features for coreference resolution
                  • Studies of knowledge sources for coreference resolution and strategies for inferring useful linguistic cues
                  • ML algorithms of coreference resolution
                  • Learning features from annotated/raw corpora
                  • Portability of English coreference resolution systems to Romance languages


After the workshop, selected papers will be published in a monographic issue of the SEPLN journal: Procesamiento del Lenguaje Natural 42 (April 2009). ISSN:1135-5948.


                  • Antonio Balvet (Université Lille 3, France)
                  • Richard Evans (University of Woverhampton, UK)
                  • Antònia Martí (Universitat de Barcelona, Spain)
                  • Patricio Martínez-Barco (Universidad de Alicante, Spain)
                  • Ruslan Mitkov (University of Woverhampton, UK)
                  • Roser Morante (University of Antwerp, Belgium)
                  • Rafael Muñoz (Universidad de Alicante, Spain)
                  • Costanza Navarretta (CST - Center for Sprogteknologi, Denmark)
                  • Constantin Orasan (University of Wolverhampton, UK)
                  • Lluís Padró (Universitat Politècnica de Catalunya, Spain)
                  • Massimo Poesio (University of Essex, UK / Università di Trento, Italy)
                  • Marta Recasens (Universitat de Barcelona, Spain)
                  • Horacio Rodríguez (Universitat Politècnica de Catalunya, Spain)
                  • Emili Sapena (Universitat Politècnica de Catalunya, Spain)
                  • Mihai Surdeanu (Yahoo! Research Barcelona, Spain)
                  • Mariona Taulé (Universitat de Barcelona, Spain)
                  • Jordi Turmo (Universitat Politècnica de Catalunya, Spain)
                  • Alfonso Ureña (Universidad de Jaén, Spain)
                  • Antal van den Bosch (Tilburg University, The Netherlands)


Abstract submission deadline: 25 September 2008
Notification of acceptance: 15 October 2008
Final version of abstracts: 1 November 2008
Workshop: 13-15 November 2008
Early version of full papers: 15 January 2009
Camera ready full papers: 23 February 2009