A Constrained Latent Variable Model for Coreference Resolution

Kai-Wei Chang, Rajhans Samdani, and Dan Roth, in EMNLP, 2013.

Poster Demo

Download the full text

Abstract

Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution. We show that L3M admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic gradient based learning. Experiments on ACE and Ontonotes data show that L3M and its constrained version, CL3M, are more accurate than several state-of-the-art approaches as well as some structured prediction models proposed in the literature.

Poster

Bib Entry

@inproceedings{ChangSaRo13,
  author = {Chang, Kai-Wei and Samdani, Rajhans and Roth, Dan},
  title = {A Constrained Latent Variable Model for Coreference Resolution},
  booktitle = {EMNLP},
  year = {2013}
}

Related Publications

A Discriminative Latent Variable Model for Online Clustering, ICML, 2014
Illinois-Coref: The UI System in the CoNLL-2012 Shared Task, CoNLL Shared Task, 2012
Inference Protocols for Coreference Resolution, CoNLL Shared Task, 2011