Corpus ID: 372666

Unsupervised Coreference Resolution in a Nonparametric Bayesian Model

@inproceedings{Haghighi2007UnsupervisedCR,
  title={Unsupervised Coreference Resolution in a Nonparametric Bayesian Model},
  author={A. Haghighi and D. Klein},
  booktitle={ACL},
  year={2007}
}

A. Haghighi, D. Klein

Published in ACL 2007

Computer Science

We present an unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric structure within each document. While most existing coreference work is driven by pairwise decisions, our model is fully generative, producing each mention from a combination of global entity properties and local attentional state. Despite being unsupervised, our system achieves a 70.3 MUC F1 measure on the MUC-6 test… CONTINUE READING

View on ACL

nlp.cs.berkeley.edu

Save to Library

Create Alert

Cite

Launch Research Feed