An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)

Qi PENG; Changmeng ZHENG; Yi CAI; Tao WANG; Haoran XIE; Qing LI

doi:10.1609/aaai.v35i18.17929

An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)

Qi PENG, Changmeng ZHENG, Yi CAI^*, Tao WANG, Haoran XIE, Qing LI

^*Corresponding author for this work

Department of Computing and Decision Sciences

Research output: Book Chapters | Papers in Conference Proceedings › Conference (Extended Abstracts) › peer-review

Abstract

Existing methods for named entity recognition are critically relied on labeled data. To handle the situation that the data is fully-unlabeled, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled source data and then adapts to unlabeled target domain. We first apply adversarial training to reduce the distribution gap between different domains. Furthermore, we introduce an entity-aware attention to guide adversarial process to achieve the alignment of entity features. The experiment shows that our model outperforms the state-of-the-art approaches.

Original language	English
Title of host publication	Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021
Publisher	Association for the Advancement of Artificial Intelligence
Pages	15865-15866
Number of pages	2
ISBN (Electronic)	9781713835974
DOIs	https://doi.org/10.1609/aaai.v35i18.17929
Publication status	Published - Feb 2021
Event	35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Online, Virtual, Online Duration: 2 Feb 2021 → 9 Feb 2021 https://ojs.aaai.org/index.php/AAAI/issue/view/399

Publication series

Name	Proceedings of the AAAI Conference on Artificial Intelligence
Publisher	Association for the Advancement of Artificial Intelligence
Number	18
Volume	35
ISSN (Print)	2159-5399
ISSN (Electronic)	2374-3468

Conference

Conference	35th AAAI Conference on Artificial Intelligence, AAAI 2021
City	Virtual, Online
Period	2/02/21 → 9/02/21
Internet address	https://ojs.aaai.org/index.php/AAAI/issue/view/399

Bibliographical note

Publisher Copyright:
Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved

Funding

This work was supported by the Fundamental Research Funds for the Central Universities, SCUT(No.D2182480), the National Key Research and Development Program of China, the Science and Technology Programs of Guangzhou (No.201802010027, 201902010046), National Natural Science Foundation of China (62076100).

Access to Document

10.1609/aaai.v35i18.17929

Cite this

PENG, Q., ZHENG, C., CAI, Y., WANG, T., XIE, H., & LI, Q. (2021). An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract). In Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021 (pp. 15865-15866). (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 35, No. 18). Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v35i18.17929

PENG, Qi ; ZHENG, Changmeng ; CAI, Yi et al. / An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract). Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021. Association for the Advancement of Artificial Intelligence, 2021. pp. 15865-15866 (Proceedings of the AAAI Conference on Artificial Intelligence; 18).

@inbook{192d8c30d2fb4fe38d1212ebb6a03091,

title = "An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)",

abstract = "Existing methods for named entity recognition are critically relied on labeled data. To handle the situation that the data is fully-unlabeled, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled source data and then adapts to unlabeled target domain. We first apply adversarial training to reduce the distribution gap between different domains. Furthermore, we introduce an entity-aware attention to guide adversarial process to achieve the alignment of entity features. The experiment shows that our model outperforms the state-of-the-art approaches.",

author = "Qi PENG and Changmeng ZHENG and Yi CAI and Tao WANG and Haoran XIE and Qing LI",

note = "Publisher Copyright: Copyright {\textcopyright} 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved; 35th AAAI Conference on Artificial Intelligence, AAAI 2021 ; Conference date: 02-02-2021 Through 09-02-2021",

year = "2021",

month = feb,

doi = "10.1609/aaai.v35i18.17929",

language = "English",

series = "Proceedings of the AAAI Conference on Artificial Intelligence",

publisher = "Association for the Advancement of Artificial Intelligence",

number = "18",

pages = "15865--15866",

booktitle = "Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021",

url = "https://ojs.aaai.org/index.php/AAAI/issue/view/399",

}

PENG, Q, ZHENG, C, CAI, Y, WANG, T, XIE, H & LI, Q 2021, An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract). in Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021. Proceedings of the AAAI Conference on Artificial Intelligence, no. 18, vol. 35, Association for the Advancement of Artificial Intelligence, pp. 15865-15866, 35th AAAI Conference on Artificial Intelligence, AAAI 2021, Virtual, Online, 2/02/21. https://doi.org/10.1609/aaai.v35i18.17929

An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract). / PENG, Qi; ZHENG, Changmeng; CAI, Yi et al.
Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021. Association for the Advancement of Artificial Intelligence, 2021. p. 15865-15866 (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 35, No. 18).

Research output: Book Chapters | Papers in Conference Proceedings › Conference (Extended Abstracts) › peer-review

TY - CHAP

T1 - An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)

AU - PENG, Qi

AU - ZHENG, Changmeng

AU - CAI, Yi

AU - WANG, Tao

AU - XIE, Haoran

AU - LI, Qing

PY - 2021/2

Y1 - 2021/2

N2 - Existing methods for named entity recognition are critically relied on labeled data. To handle the situation that the data is fully-unlabeled, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled source data and then adapts to unlabeled target domain. We first apply adversarial training to reduce the distribution gap between different domains. Furthermore, we introduce an entity-aware attention to guide adversarial process to achieve the alignment of entity features. The experiment shows that our model outperforms the state-of-the-art approaches.

AB - Existing methods for named entity recognition are critically relied on labeled data. To handle the situation that the data is fully-unlabeled, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled source data and then adapts to unlabeled target domain. We first apply adversarial training to reduce the distribution gap between different domains. Furthermore, we introduce an entity-aware attention to guide adversarial process to achieve the alignment of entity features. The experiment shows that our model outperforms the state-of-the-art approaches.

UR - http://www.scopus.com/inward/record.url?scp=85130040069&partnerID=8YFLogxK

U2 - 10.1609/aaai.v35i18.17929

DO - 10.1609/aaai.v35i18.17929

M3 - Conference (Extended Abstracts)

AN - SCOPUS:85130040069

T3 - Proceedings of the AAAI Conference on Artificial Intelligence

SP - 15865

EP - 15866

BT - Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021

PB - Association for the Advancement of Artificial Intelligence

T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021

Y2 - 2 February 2021 through 9 February 2021

ER -

PENG Q, ZHENG C, CAI Y, WANG T, XIE H, LI Q. An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract). In Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021. Association for the Advancement of Artificial Intelligence. 2021. p. 15865-15866. (Proceedings of the AAAI Conference on Artificial Intelligence; 18). doi: 10.1609/aaai.v35i18.17929

An Entity-Aware Adversarial Domain Adaptation Network for Cross-Domain Named Entity Recognition (Student Abstract)

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this