Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction

Thien Huu Nguyen; Barbara Plank; Ralph Grishman

doi:10.3115/v1/p15-1062

Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction

Thien Huu Nguyen, Barbara Plank, Ralph Grishman

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We study the application of word embeddings to generate semantic representations for the domain adaptation problem of relation extraction (RE) in the tree kernelbased method. We systematically evaluate various techniques to generate the semantic representations and demonstrate that they are effective to improve the generalization performance of a tree kernel-based relation extractor across domains (up to 7% relative improvement). In addition, we compare the tree kernel-based and the feature-based method for RE in a compatible way, on the same resources and settings, to gain insights into which kind of system is more robust to domain changes. Our results and error analysis shows that the tree kernel-based method outperforms the feature-based approach.

Original language	English (US)
Title of host publication	ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	635-644
Number of pages	10
ISBN (Electronic)	9781941643723
DOIs	https://doi.org/10.3115/v1/p15-1062
State	Published - 2015
Event	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China Duration: Jul 26 2015 → Jul 31 2015

Publication series

Name	ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Volume	1

Other

Other	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
Country/Territory	China
City	Beijing
Period	7/26/15 → 7/31/15

ASJC Scopus subject areas

Artificial Intelligence
Software

Access to Document

10.3115/v1/p15-1062

Cite this

Nguyen, T. H., Plank, B., & Grishman, R. (2015). Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (pp. 635-644). (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference; Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p15-1062

Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction. / Nguyen, Thien Huu; Plank, Barbara; Grishman, Ralph.
ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. p. 635-644 (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nguyen, TH, Plank, B & Grishman, R 2015, Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference, vol. 1, Association for Computational Linguistics (ACL), pp. 635-644, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 7/26/15. https://doi.org/10.3115/v1/p15-1062

Nguyen TH, Plank B, Grishman R. Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2015. p. 635-644. (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference). doi: 10.3115/v1/p15-1062

Nguyen, Thien Huu ; Plank, Barbara ; Grishman, Ralph. / Semantic representations for domain adaptation : A case study on the tree kernel-based method for relation extraction. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. pp. 635-644 (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference).

@inproceedings{d00d05e728ec4230bfcd5c7bb241f0f3,

title = "Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction",

abstract = "We study the application of word embeddings to generate semantic representations for the domain adaptation problem of relation extraction (RE) in the tree kernelbased method. We systematically evaluate various techniques to generate the semantic representations and demonstrate that they are effective to improve the generalization performance of a tree kernel-based relation extractor across domains (up to 7% relative improvement). In addition, we compare the tree kernel-based and the feature-based method for RE in a compatible way, on the same resources and settings, to gain insights into which kind of system is more robust to domain changes. Our results and error analysis shows that the tree kernel-based method outperforms the feature-based approach.",

author = "Nguyen, {Thien Huu} and Barbara Plank and Ralph Grishman",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computationl Linguisticss.; 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 ; Conference date: 26-07-2015 Through 31-07-2015",

year = "2015",

doi = "10.3115/v1/p15-1062",

language = "English (US)",

series = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "635--644",

booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - Semantic representations for domain adaptation

T2 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015

AU - Nguyen, Thien Huu

AU - Plank, Barbara

AU - Grishman, Ralph

PY - 2015

Y1 - 2015

N2 - We study the application of word embeddings to generate semantic representations for the domain adaptation problem of relation extraction (RE) in the tree kernelbased method. We systematically evaluate various techniques to generate the semantic representations and demonstrate that they are effective to improve the generalization performance of a tree kernel-based relation extractor across domains (up to 7% relative improvement). In addition, we compare the tree kernel-based and the feature-based method for RE in a compatible way, on the same resources and settings, to gain insights into which kind of system is more robust to domain changes. Our results and error analysis shows that the tree kernel-based method outperforms the feature-based approach.

AB - We study the application of word embeddings to generate semantic representations for the domain adaptation problem of relation extraction (RE) in the tree kernelbased method. We systematically evaluate various techniques to generate the semantic representations and demonstrate that they are effective to improve the generalization performance of a tree kernel-based relation extractor across domains (up to 7% relative improvement). In addition, we compare the tree kernel-based and the feature-based method for RE in a compatible way, on the same resources and settings, to gain insights into which kind of system is more robust to domain changes. Our results and error analysis shows that the tree kernel-based method outperforms the feature-based approach.

UR - http://www.scopus.com/inward/record.url?scp=84943777848&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943777848&partnerID=8YFLogxK

U2 - 10.3115/v1/p15-1062

DO - 10.3115/v1/p15-1062

M3 - Conference contribution

AN - SCOPUS:84943777848

T3 - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

SP - 635

EP - 644

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

Y2 - 26 July 2015 through 31 July 2015

ER -

Semantic representations for domain adaptation: A case study on the tree kernel-based method for relation extraction

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this