On the issue of combining anaphoricity determination and antecedent identification in anaphora resolution

We propose a machine learning-based approach to noun phrase anaphora resolution that combines the advantages of previous learning-based models while overcoming their drawbacks. Our anaphora resolution process reverses the order of the steps in the classification-and-search model proposed by Ng and Cardie, but inherits all the advantages of that model. We conducted experiments on resolving noun phrase anaphora in Japanese. The results show that with the classification-and-search based modifications, our proposed model outperforms earlier learning-based approaches.