Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision

doi:10.1007/s11390-022-1479-0

	Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision
	Bai, Gui-Rong1,2 ; Liu, Qing-Bin1,2 ; He, Shi-Zhu1 ; Liu, Kang1,2 ; Zhao, Jun1,2
发表期刊	JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
ISSN	1000-9000
	2023-12-01
卷号	38 期号:6 页码:1237-1249
通讯作者	He, Shi-Zhu(shizhu.he@nlpr.ia.ac.cn)
摘要	Although neural approaches have yielded state-of-the-art results in the sentence matching task, their performance inevitably drops dramatically when applied to unseen domains. To tackle this cross-domain challenge, we address unsupervised domain adaptation on sentence matching, in which the goal is to have good performance on a target domain with only unlabeled target domain data as well as labeled source domain data. Specifically, we propose to perform self-supervised tasks to achieve it. Different from previous unsupervised domain adaptation methods, self-supervision can not only flexibly suit the characteristics of sentence matching with a special design, but also be much easier to optimize. When training, each self-supervised task is performed on both domains simultaneously in an easy-to-hard curriculum, which gradually brings the two domains closer together along the direction relevant to the task. As a result, the classifier trained on the source domain is able to generalize to the unlabeled target domain. In total, we present three types of self-supervised tasks and the results demonstrate their superiority. In addition, we further study the performance of different usages of self-supervised tasks, which would inspire how to effectively utilize self-supervision for cross-domain scenarios.
关键词	unsupervised domain adaptation sentence matching self-supervision
DOI	10.1007/s11390-022-1479-0
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61922085] ; National Natural Science Foundation of China[61976211] ; National Key Research and Development Program of China[2020AAA0106400] ; Key Research Program of the Chinese Academy of Sciences[ZDBS-SSW-JSC006] ; Independent Research Project of the National Laboratory of Pattern Recognition[Z-2018013] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2020138]
项目资助者	National Natural Science Foundation of China ; National Key Research and Development Program of China ; Key Research Program of the Chinese Academy of Sciences ; Independent Research Project of the National Laboratory of Pattern Recognition ; Youth Innovation Promotion Association of Chinese Academy of Sciences
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS记录号	WOS:001154653300002
出版者	SPRINGER SINGAPORE PTE LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55531
专题	复杂系统认知与决策实验室
通讯作者	He, Shi-Zhu
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Bai, Gui-Rong,Liu, Qing-Bin,He, Shi-Zhu,et al. Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2023,38(6):1237-1249.
APA	Bai, Gui-Rong,Liu, Qing-Bin,He, Shi-Zhu,Liu, Kang,&Zhao, Jun.(2023).Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,38(6),1237-1249.
MLA	Bai, Gui-Rong,et al."Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 38.6(2023):1237-1249.