Domain adaptation for coreference resolution: An adaptive ensemble approach

Yang, JB; Mao, Q; Xiang, QL; Tsang, IW; Chai, KMA; Chieu, HL

Domain adaptation for coreference resolution: An adaptive ensemble approach

Yang, JB Mao, Q Xiang, QL Tsang, IW

Chai, KMA Chieu, HL

Permalink

Publication Type:: Conference Proceeding
Citation:: EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference, 2012, pp. 744 - 753
Issue Date:: 2012-12-01

Closed Access

	Filename	Description	Size
	domain.pdf	Published version	658.02 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yang, JB	en_US
dc.contributor.author	Mao, Q	en_US
dc.contributor.author	Xiang, QL	en_US
dc.contributor.author	Tsang, IW https://orcid.org/0000-0001-8095-4637	en_US
dc.contributor.author	Chai, KMA	en_US
dc.contributor.author	Chieu, HL	en_US
dc.date.issued	2012-12-01	en_US
dc.identifier.citation	EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference, 2012, pp. 744 - 753	en_US
dc.identifier.isbn	9781937284435	en_US
dc.identifier.uri	http://hdl.handle.net/10453/121285
dc.description.abstract	We propose an adaptive ensemble method to adapt coreference resolution across domains. This method has three features: (1) it can optimize for any user-specified objective measure; (2) it can make document-specific prediction rather than rely on a fixed base model or a fixed set of base models; (3) it can automatically adjust the active ensemble members during prediction. With simplification, this method can be used in the traditional within-domain case, while still retaining the above features. To the best of our knowledge, this work is the first to both (i) develop a domain adaptation algorithm for the coreference resolution problem and (ii) have the above features as an ensemble method. Empirically, we show the benefits of (i) on the six domains of the ACE 2005 data set in domain adaptation setting, and of (ii) on both the MUC-6 and the ACE 2005 data sets in within-domain setting. © 2012 Association for Computational Linguistics.	en_US
dc.relation.ispartof	EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference	en_US
dc.title	Domain adaptation for coreference resolution: An adaptive ensemble approach	en_US
dc.type	Conference Proceeding
utslib.for	080101 Adaptive Agents and Intelligent Robotics	en_US
utslib.for	080109 Pattern Recognition and Data Mining	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

We propose an adaptive ensemble method to adapt coreference resolution across domains. This method has three features: (1) it can optimize for any user-specified objective measure; (2) it can make document-specific prediction rather than rely on a fixed base model or a fixed set of base models; (3) it can automatically adjust the active ensemble members during prediction. With simplification, this method can be used in the traditional within-domain case, while still retaining the above features. To the best of our knowledge, this work is the first to both (i) develop a domain adaptation algorithm for the coreference resolution problem and (ii) have the above features as an ensemble method. Empirically, we show the benefits of (i) on the six domains of the ACE 2005 data set in domain adaptation setting, and of (ii) on both the MUC-6 and the ACE 2005 data sets in within-domain setting. © 2012 Association for Computational Linguistics.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/121285