Zero-Anaphora Resolution by Learning Rich Syntactic Pattern Features

摘要

We approach the zero-anaphora resolution problem by decomposing it into intrasentential and intersentential zero-anaphora resolution tasks. For the former task, syntactic patterns of zero-pronouns and their antecedents are useful clues. Taking Japanese as a target language, we empirically demonstrate that incorporating rich syntactic pattern features in a state-of-the-art learning-based anaphora resolution model dramatically improves the accuracy of intrasentential zero-anaphora, which consequently improves the overall performance of zero-anaphora resolution.