UDAA: An Unsupervised Domain Adaptation Adversarial Learning Framework for Zero-Resource Cross-Domain Named Entity Recognition

Li Baofeng, Tang Jianguo, Qin Yu, Xu Yuelou, Lu Yan, Wang Kai, Li Lei, Zhou Yanquan


Abstract
“The zero-resource cross-domain named entity recognition (NER) task aims to perform NER in aspecific domain where labeled data is unavailable. Existing methods primarily focus on transfer-ring NER knowledge from high-resource to zero-resource domains. However, the challenge liesin effectively transferring NER knowledge between domains due to the inherent differences inentity structures across domains. To tackle this challenge, we propose an Unsupervised DomainAdaptation Adversarial (UDAA) framework, which combines the masked language model auxil-iary task with the domain adaptive adversarial network to mitigate inter-domain differences andefficiently facilitate knowledge transfer. Experimental results on CBS, Twitter, and WNUT2016three datasets demonstrate the effectiveness of our framework. Notably, we achieved new state-of-the-art performance on the three datasets. Our code will be released.Introduction”
Anthology ID:
2024.ccl-1.87
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Maosong Sun, Jiye Liang, Xianpei Han, Zhiyuan Liu, Yulan He
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
1123–1135
Language:
English
URL:
https://aclanthology.org/2024.ccl-1.87/
DOI:
Bibkey:
Cite (ACL):
Li Baofeng, Tang Jianguo, Qin Yu, Xu Yuelou, Lu Yan, Wang Kai, Li Lei, and Zhou Yanquan. 2024. UDAA: An Unsupervised Domain Adaptation Adversarial Learning Framework for Zero-Resource Cross-Domain Named Entity Recognition. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 1123–1135, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
UDAA: An Unsupervised Domain Adaptation Adversarial Learning Framework for Zero-Resource Cross-Domain Named Entity Recognition (Baofeng et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-1.87.pdf