Incorporating Contextual Cues in Trainable Models for Coreference Resolution
Ryu Iida, Kentaro Inui, Hiroya Takamura, Yūji Matsumoto · 2003
We propose a method that incorporates various novel contextual cues into a machine learning for resolving coreference. Distinct characteristics of our model are (i) incorporating more linguistic features capturing contextual information that is more sophisticated than what is offered in Centering Theory, and (ii) a tournament model for selecting a referent. Our experiments show that this model significantly outperforms earlier machine learning approaches, such as Soon et al. (2001). 1