Paper: Coreference Resolution in a Modular Entity-Centered Model

ACL ID N10-1061
Title Coreference Resolution in a Modular Entity-Centered Model
Venue Human Language Technologies
Session Main Conference
Year 2010
Authors

Coreference resolution is governed by syntac- tic, semantic, and discourse constraints. We present a generative, model-based approach in which each of these factors is modularly en- capsulated and learned in a primarily unsu- pervised manner. Our semantic representation first hypothesizes an underlying set of latent entity types, which generate specific entities that in turn render individual mentions. By sharing lexical statistics at the level of abstract entity types, our model is able to substantially reduce semantic compatibility errors, result- ing in the best results to date on the complete end-to-end coreference task.