Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation

Huiyun Yang, Shujian Huang, Xin-Yu Dai, Jiajun Chen


Abstract
In sequence labeling, previous domain adaptation methods focus on the adaptation from the source domain to the entire target domain without considering the diversity of individual target domain samples, which may lead to negative transfer results for certain samples. Besides, an important characteristic of sequence labeling tasks is that different elements within a given sample may also have diverse domain relevance, which requires further consideration. To take the multi-level domain relevance discrepancy into account, in this paper, we propose a fine-grained knowledge fusion model with the domain relevance modeling scheme to control the balance between learning from the target domain data and learning from the source domain model. Experiments on three sequence labeling tasks show that our fine-grained knowledge fusion model outperforms strong baselines and other state-of-the-art sequence labeling domain adaptation methods.
Anthology ID:
D19-1429
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4197–4206
Language:
URL:
https://aclanthology.org/D19-1429
DOI:
10.18653/v1/D19-1429
Bibkey:
Cite (ACL):
Huiyun Yang, Shujian Huang, Xin-Yu Dai, and Jiajun Chen. 2019. Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4197–4206, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation (Yang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1429.pdf