Corpus-based anaphora resolution towards antecedent preference

要旨

In this paper we propose a corpus-based approach to anaphora resolution combining a machine learning method and statistical information. First, a decision tree trained on an annotated corpus determines the coreference relation of a given anaphor and antecedent candidates and is utilized as a filter in order to reduce the number of potential candidates. In the second step, preference selection is achieved by taking into account the frequency information of coreferential and non-referential pairs tagged in the training corpus as well as distance features within the current discourse. Preliminary experiments concerning the resolution of Japanese pronouns in spoken-language dialogs result in a success rate of 80.6%.

主題