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

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

Biostatistics & Health Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › 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	AAAI21
Publication status	Published - 3 Dec 2020

Access to Document

https://www.aaai.org/AAAI21Papers/SA-237.PengQ.pdfLicence: CC BY-NC

Cite this

@inbook{5fb61143bff844b6b60141b3586fd992,

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 betweendifferent 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",

year = "2020",

month = dec,

day = "3",

language = "English",

booktitle = "AAAI21",

}

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 - 2020/12/3

Y1 - 2020/12/3

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 betweendifferent 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 betweendifferent 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.

M3 - Conference paper

BT - AAAI21

ER -

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

Abstract

Access to Document

Fingerprint

Cite this