Named entity recognition for novel types by transfer learning

Lizhen Qu; Gabriela Ferraro; Liyuan Zhou; Weiwei Hou; Timothy Baldwin

doi:10.18653/v1/D16-1087

Named entity recognition for novel types by transfer learning

Lizhen Qu
, Gabriela Ferraro
, Liyuan Zhou
, Weiwei Hou
, Timothy Baldwin

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

33 Citations (Scopus)

Abstract

In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.

Original language	English
Title of host publication	EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Conference Proceedings
Editors	Xavier Carreras, Kevin Duh
Place of Publication	Red Hook NY USA
Publisher	Association for Computational Linguistics (ACL)
Pages	899-905
Number of pages	7
ISBN (Electronic)	9781945626258
DOIs	https://doi.org/10.18653/v1/D16-1087
Publication status	Published - 2016
Externally published	Yes
Event	Empirical Methods in Natural Language Processing 2016 - Austin, United States of America Duration: 1 Nov 2016 → 5 Nov 2016 https://www.aclweb.org/mirror/emnlp2016/ https://www.aclweb.org/anthology/volumes/D16-1/ (Proceedings)

Conference

Conference	Empirical Methods in Natural Language Processing 2016
Abbreviated title	EMNLP 2016
Country/Territory	United States of America
City	Austin
Period	1/11/16 → 5/11/16
Internet address	https://www.aclweb.org/mirror/emnlp2016/ https://www.aclweb.org/anthology/volumes/D16-1/ (Proceedings)

Access to Document

10.18653/v1/D16-1087

288980330-oaFinal published version, 262 KB

Cite this

@inproceedings{8dcd4c0cd7c14f7b89944c1cd6c18cb5,

title = "Named entity recognition for novel types by transfer learning",

abstract = "In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.",

author = "Lizhen Qu and Gabriela Ferraro and Liyuan Zhou and Weiwei Hou and Timothy Baldwin",

year = "2016",

doi = "10.18653/v1/D16-1087",

language = "English",

pages = "899--905",

editor = "Carreras, \{Xavier \} and Kevin Duh",

booktitle = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Conference Proceedings",

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

note = "Empirical Methods in Natural Language Processing 2016, EMNLP 2016 ; Conference date: 01-11-2016 Through 05-11-2016",

url = "https://www.aclweb.org/mirror/emnlp2016/, https://www.aclweb.org/anthology/volumes/D16-1/",

}

Qu, L, Ferraro, G, Zhou, L, Hou, W & Baldwin, T 2016, Named entity recognition for novel types by transfer learning. in X Carreras & K Duh (eds), EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Conference Proceedings. Association for Computational Linguistics (ACL), Red Hook NY USA, pp. 899-905, Empirical Methods in Natural Language Processing 2016, Austin, Texas, United States of America, 1/11/16. https://doi.org/10.18653/v1/D16-1087

Named entity recognition for novel types by transfer learning. / Qu, Lizhen; Ferraro, Gabriela; Zhou, Liyuan et al.
EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Conference Proceedings. ed. / Xavier Carreras; Kevin Duh. Red Hook NY USA: Association for Computational Linguistics (ACL), 2016. p. 899-905.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Named entity recognition for novel types by transfer learning

AU - Qu, Lizhen

AU - Ferraro, Gabriela

AU - Zhou, Liyuan

AU - Hou, Weiwei

AU - Baldwin, Timothy

PY - 2016

Y1 - 2016

N2 - In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.

AB - In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.

UR - https://www.scopus.com/pages/publications/85021835278

U2 - 10.18653/v1/D16-1087

DO - 10.18653/v1/D16-1087

M3 - Conference Paper

SP - 899

EP - 905

BT - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Conference Proceedings

A2 - Carreras, Xavier

A2 - Duh, Kevin

PB - Association for Computational Linguistics (ACL)

CY - Red Hook NY USA

T2 - Empirical Methods in Natural Language Processing 2016

Y2 - 1 November 2016 through 5 November 2016

ER -

Named entity recognition for novel types by transfer learning

Abstract

Conference

Access to Document

Other files and links

Cite this