Employing word representations and regularization for domain adaptation of relation extraction

Thien Huu Nguyen, Ralph Grishman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Relation extraction suffers from a performance loss when a model is applied to out-of-domain data. This has fostered the development of domain adaptation techniques for relation extraction. This paper evaluates word embeddings and clustering on adapting feature-based relation extraction systems. We systematically explore various ways to apply word embeddings and show the best adaptation improvement by combining word cluster and word embedding information. Finally, we demonstrate the effectiveness of regularization for the adaptability of relation extractors.

Original languageEnglish (US)
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages68-74
Number of pages7
Volume2
ISBN (Print)9781937284732
StatePublished - 2014
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: Jun 22 2014Jun 27 2014

Other

Other52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
CountryUnited States
CityBaltimore, MD
Period6/22/146/27/14

Fingerprint

performance
Adaptability

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Nguyen, T. H., & Grishman, R. (2014). Employing word representations and regularization for domain adaptation of relation extraction. In Long Papers (Vol. 2, pp. 68-74). Association for Computational Linguistics (ACL).

Employing word representations and regularization for domain adaptation of relation extraction. / Nguyen, Thien Huu; Grishman, Ralph.

Long Papers. Vol. 2 Association for Computational Linguistics (ACL), 2014. p. 68-74.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nguyen, TH & Grishman, R 2014, Employing word representations and regularization for domain adaptation of relation extraction. in Long Papers. vol. 2, Association for Computational Linguistics (ACL), pp. 68-74, 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, United States, 6/22/14.
Nguyen TH, Grishman R. Employing word representations and regularization for domain adaptation of relation extraction. In Long Papers. Vol. 2. Association for Computational Linguistics (ACL). 2014. p. 68-74
Nguyen, Thien Huu ; Grishman, Ralph. / Employing word representations and regularization for domain adaptation of relation extraction. Long Papers. Vol. 2 Association for Computational Linguistics (ACL), 2014. pp. 68-74
@inproceedings{55c634c53a8a435bb791cf77e6a41f1c,
title = "Employing word representations and regularization for domain adaptation of relation extraction",
abstract = "Relation extraction suffers from a performance loss when a model is applied to out-of-domain data. This has fostered the development of domain adaptation techniques for relation extraction. This paper evaluates word embeddings and clustering on adapting feature-based relation extraction systems. We systematically explore various ways to apply word embeddings and show the best adaptation improvement by combining word cluster and word embedding information. Finally, we demonstrate the effectiveness of regularization for the adaptability of relation extractors.",
author = "Nguyen, {Thien Huu} and Ralph Grishman",
year = "2014",
language = "English (US)",
isbn = "9781937284732",
volume = "2",
pages = "68--74",
booktitle = "Long Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Employing word representations and regularization for domain adaptation of relation extraction

AU - Nguyen, Thien Huu

AU - Grishman, Ralph

PY - 2014

Y1 - 2014

N2 - Relation extraction suffers from a performance loss when a model is applied to out-of-domain data. This has fostered the development of domain adaptation techniques for relation extraction. This paper evaluates word embeddings and clustering on adapting feature-based relation extraction systems. We systematically explore various ways to apply word embeddings and show the best adaptation improvement by combining word cluster and word embedding information. Finally, we demonstrate the effectiveness of regularization for the adaptability of relation extractors.

AB - Relation extraction suffers from a performance loss when a model is applied to out-of-domain data. This has fostered the development of domain adaptation techniques for relation extraction. This paper evaluates word embeddings and clustering on adapting feature-based relation extraction systems. We systematically explore various ways to apply word embeddings and show the best adaptation improvement by combining word cluster and word embedding information. Finally, we demonstrate the effectiveness of regularization for the adaptability of relation extractors.

UR - http://www.scopus.com/inward/record.url?scp=84906930736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906930736&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84906930736

SN - 9781937284732

VL - 2

SP - 68

EP - 74

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

ER -