Bilingual alignment of anaphoric expressions
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC 2002)
Abstract
In this paper we present an automatic mechanism for bilingual (Spanish-English) alignment of anaphoric expressions. For this purpose, two anaphora resolution systems were used. Both are based on linguistic preferences and constraints, for Spanish (SUPPAR) and for English (MARS). These systems have been independently developed and each of them is presented individually with their evaluation results. The majority of the paper presents an automatic alignment method for pronominal anaphora in Spanish and English. Once an anaphor has been solved (in both languages) this method matches anaphoric expressions and antecedents from both texts. A bitext map method has been used for the alignment with a set of bilingual texts for the evaluation. These texts have been extracted from several European Community Official documents (EUR-lex database). The alignment mechanism can be applied to different tasks related to Machine Translation such us pattern learning for translation or evaluation for automatic generation of multilingual anaphora.