Combining the best of two worlds: a hybrid approach to multilingual coreference resolution

Authors:
Chen Chen;Vincent Ng
Affiliations:
University of Texas at Dallas, Richardson, TX;University of Texas at Dallas, Richardson, TX
Venue:
CoNLL '12 Joint Conference on EMNLP and CoNLL - Shared Task
Year:
2012

Citing 8
Cited 1

Learning noun phrase anaphoricity to improve coreference resolution: issues in representation and optimization

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Graph-cut-based anaphoricity determination for coreference resolution

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Simple coreference resolution with rich syntactic and semantic features

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
SemEval-2010 task 1: Coreference resolution in multiple languages

SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
Coreference resolution with world knowledge

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Narrowing the modeling gap: a cluster-ranking approach to coreference resolution

Journal of Artificial Intelligence Research
Stanford's multi-pass sieve coreference resolution system at the CoNLL-2011 shared task

CONLL Shared Task '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task
CoNLL-2012 shared task: Modeling Multilingual Unrestricted Coreference in OntoNotes

CoNLL '12 Joint Conference on EMNLP and CoNLL - Shared Task

Deterministic coreference resolution based on entity-centric, precision-ranked rules

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

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, which combines 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.