Statistical Anaphora Resolution in Biomedical Texts

This paper presents a probabilistic model for resolution of non-pronominal anaphora in biomedical texts. The model seeks to find the antecedents of anaphoric expressions, both coreferent and associative ones, and also to identify discourse-new expressions. We consider only the noun phrases referring to biomedical entities. The model reaches state-of-the art performance: 5669% precision and 54-67% recall on coreferent cases, and reasonable performance on different classes of associative cases.

• Type: Conference
• Year: 2008
• Where: COLING
• Authors: Caroline Gasperin, Ted Briscoe
• Keywords: Anaphoric Expressions, Associative Ones, COLING 2008, Computational Linguistics, State-of-the Art Performance