Anaphora Resolution in Biomedical Literature: A Hybrid Approach

While traditional work on anaphora resolution has focused on resolving anaphors in newspaper and newswire articles, the surge of interest in biomedical natural language pro-cessing in recent years has stimulated work on anaphora resolution in biomedical texts. Existing anaphora resolvers, whether applied to the biomedical domain or not, have adopted either a learning-based or a rule-based approach. We hy-pothesize that both approaches have their unique strengths, and propose in this paper a hybrid approach to anaphora resolution in biomedical texts that aims to combine their strengths. Our hybrid approach achieves an F-score of 60.9 on the BioNLP-2011 coreference dataset, which to our knowl-edge is the best result reported to date on this dataset