Inference protocols for coreference resolution

Authors:
Kai-Wei Chang;Rajhans Samdani;Alla Rozovskaya;Nick Rizzolo;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;University of Illinois at Urbana-Champaign
Venue:
CONLL Shared Task '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task
Year:
2011

Citing 5
Cited 6

Correlation Clustering

FOCS '02 Proceedings of the 43rd Symposium on Foundations of Computer Science
Supervised clustering with support vector machines

ICML '05 Proceedings of the 22nd international conference on Machine learning
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
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

Joint learning for coreference resolution with Markov logic

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
A mixed deterministic model for coreference resolution

CoNLL '12 Joint Conference on EMNLP and CoNLL - Shared Task
Illinois-Coref: the UI system in the CoNLL-2012 shared task

CoNLL '12 Joint Conference on EMNLP and CoNLL - Shared Task
Hybrid rule-based algorithm for coreference resolution

CoNLL '12 Joint Conference on EMNLP and CoNLL - Shared Task
End-to-end coreference resolution for clinical narratives

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Deterministic coreference resolution based on entity-centric, precision-ranked rules

Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents Illinois-Coref, a system for coreference resolution that participated in the CoNLL-2011 shared task. We investigate two inference methods, Best-Link and All-Link, along with their corresponding, pairwise and structured, learning protocols. Within these, we provide a flexible architec-ture for incorporating linguistically-motivated constraints, several of which we developed and integrated. We compare and evaluate the inference approaches and the contribution of constraints, analyze the mistakes of the system, and discuss the challenges of resolving coreference for the OntoNotes-4.0 data set.