Unsupervised cross-domain named entity recognition using entity-aware adversarial training

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

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review


The success of neural network based methods in named entity recognition (NER) is heavily relied on abundant manual labeled data. However, these NER methods are unavailable when the data is fully-unlabeled in a new domain. To address the problem, we propose an unsupervised cross-domain model which leverages labeled data from source domain to predict entities in unlabeled target domain. To relieve the distribution divergence when transferring knowledge from source to target domain, we apply adversarial training. Furthermore, we design an entity-aware attention module to guide the adversarial training to reduce the discrepancy of entity features between different domains. Experimental results demonstrate that our model outperforms other methods and achieves state-of-the-art performance.
Original languageEnglish
Pages (from-to)68-77
JournalNeural Networks
Early online date31 Dec 2020
Publication statusE-pub ahead of print - 31 Dec 2020

Bibliographical note

All authors contribute equally to the article.

This work was supported by the Fundamental Research Funds for the Central Universities, SCUT (No. 2017ZD048, D2182480), the Science and Technology Planning Project of Guangdong Province (No. 2017B050506004), the Science and Technology Programs of Guangzhou (No. 201704030076, 201802010027, 201902010046) and the Hong Kong Research Grants Council (project no. C1031-18G).

Fingerprint Dive into the research topics of 'Unsupervised cross-domain named entity recognition using entity-aware adversarial training'. Together they form a unique fingerprint.

Cite this