Combining the Best of Two Worlds: A Hybrid Approach to Multilingual Coreference Resolution

Chen Chen and Vincent Ng.
Proceedings of the 2012 Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning: Shared Task, pp. 56-63, 2012.

Click here for the PostScript or PDF version. The talk slides are available here.

Abstract

We describe our system for the CoNLL-2012 shared task, which seeks to model coreference in OntoNotes for English, Chinese, and Arabic. We adopt a hybrid approach to coreference resolution, combining the strengths of rule-based methods and learning-based methods. Our official combined score over all three languages is 56.35. In particular, our score on the Chinese test set is the best among the participating teams.

Software

SinoBerryPicker, the Chinese coreference system described in the paper, can be downloaded from this page.

BibTeX entry

@InProceedings{Chen+Ng:12a,
  author = {Chen Chen and Vincent Ng},
  title = {Combining the Best of Two Worlds: A Hybrid Approach to Multilingual Coreference Resolution},
  booktitle = {Joint Conference on EMNLP and CoNLL: Proceedings of the Shared Task},
  pages = {56--63}, 
  year = 2012
}