Publication:
Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution

Thumbnail Image

Date

2015

Published Version

Journal Title

Journal ISSN

Volume Title

Publisher

Association for Computational Linguistics
The Harvard community has made this article openly available. Please share how this access benefits you.

Research Projects

Organizational Units

Journal Issue

Citation

Wiseman, Sam, Alexander M. Rush, Stuart M. Shieber, and Jason Weston. 2015. Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL-IJCNLP 2015), Beijing, China, July 26-31, 2016, 1416-1426.

Research Data

Abstract

We introduce a simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which we encourage by pre-training on a pair of corresponding subtasks. Although we use only simple, unconjoined features, the model is able to learn useful representations, and we report the best overall score on the CoNLL 2012 English test set to date.

Description

Keywords

Terms of Use

This article is made available under the terms and conditions applicable to Open Access Policy Articles (OAP), as set forth at Terms of Service

Endorsement

Review

Supplemented By

Referenced By

Related Stories