AAAI

Association for the Advancement of Artificial Intelligence

Home > Proceedings / Proceedings of the AAAI Conference on Artificial Intelligence, 35 > No. 18: AAAI-21 Student Papers and Demonstrations

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

Authors

Qi Peng

School of Software Engineering, South China University of Technology, Guangzhou, China Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education


Changmeng Zheng

School of Software Engineering, South China University of Technology, Guangzhou, China Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education


Yi Cai

School of Software Engineering, South China University of Technology, Guangzhou, China Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education


Tao Wang

Department of Biostatistics and Health Informatics, King's College London


Haoran Xie

Department of Computing and Decision Sciences, Lingnan University, Hong Kong, China


Qing Li

Department of Computing, Hong Kong Polytechnic University, Hong Kong, China


Proceedings:

No. 18: AAAI-21 Student Papers and Demonstrations

Volume

Issue:

Proceedings of the AAAI Conference on Artificial Intelligence, 35

Track:

AAAI Student Abstract and Poster Program

Downloads:

Download PDF

Abstract:

Existing methods for named entity recognition (NER) are critically relied on the amount of labeled data. However, these methods suffer from performance decline in a new domain which is fully-unlabeled. To handle the situation, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled data from source domain 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 to achieve the alignment of entity features. The experimental results show that our model outperforms the state-of-the-art approaches.

DOI:

10.1609/aaai.v35i18.17929


AAAI

Proceedings of the AAAI Conference on Artificial Intelligence, 35