Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution

This paper explores how to apply the notion of caching introduced by Walker (1996) to the task of zero-anaphora resolution. We propose a machine learning-based implementation of a cache model to reduce the computational cost of identifying an antecedent. Our empirical evaluation with Japanese newspaper articles shows that the number of candidate antecedents for each zero-pronoun can be dramatically reduced while preserving the accuracy of resolving it.