Improving pronoun resolution using statistics-based semantic compatibility information

Abstract

In this paper we focus on how to improve pronoun resolution using the statisticsbased semantic compatibility information. We investigate two unexplored issues that influence the effectiveness of such information: statistics source and learning framework. Specifically, we for the first time propose to utilize the web and the twin-candidate model, in addition to the previous combination of the corpus and the single-candidate model, to compute and apply the semantic information. Our study shows that the semantic compatibility obtained from the web can be effectively incorporated in the twin-candidate learning model and significantly improve the resolution of neutral pronouns. © 2005 Association for Computational Linguistics.