King's College London

Research portal

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

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Qi Peng, Changmeng Zheng, Yi Cai, Tao Wang, Haoran Xie, Qing Li

Original languageEnglish
Title of host publicationAAAI21
Published3 Dec 2020

King's Authors

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.

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454