Illinois-Coref: the UI system in the CoNLL-2012 shared task

Authors:
Kai-Wei Chang;Rajhans Samdani;Alla Rozovskaya;Mark Sammons;Dan Roth
Affiliations:
University of Illinois at Urbana-Champaign;University of Illinois at Urbana-Champaign;University of Illinois at Urbana-Champaign;University of Illinois at Urbana-Champaign;University of Illinois at Urbana-Champaign
Venue:
CoNLL '12 Joint Conference on EMNLP and CoNLL - Shared Task
Year:
2012

Citing 8
Cited 0

Unrestricted Coreference: Identifying Entities and Events in OntoNotes

ICSC '07 Proceedings of the International Conference on Semantic Computing
Understanding the value of features for coreference resolution

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A ranking approach to pronoun resolution

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Narrowing the modeling gap: a cluster-ranking approach to coreference resolution

Journal of Artificial Intelligence Research
CoNLL-2011 shared task: modeling unrestricted coreference in OntoNotes

CONLL Shared Task '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task
Inference protocols for coreference resolution

CONLL Shared Task '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task
Online latent structure training for language acquisition

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
CoNLL-2012 shared task: Modeling Multilingual Unrestricted Coreference in OntoNotes

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

The CoNLL-2012 shared task is an extension of the last year's coreference task. We participated in the closed track of the shared tasks in both years. In this paper, we present the improvements of Illinois-Coref system from last year. We focus on improving mention detection and pronoun coreference resolution, and present a new learning protocol. These new strategies boost the performance of the system by 5% MUC F1, 0.8% BCUB F1, and 1.7% CEAF F1 on the OntoNotes-5.0 development set.