Distribution Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains

doi:10.1109/TASLP.2022.3145289

	Distribution Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains
	Yu, Weijie 1; Xu, Chen 2; Xu, Jun 2; Pang, Liang 3; Wen, Ji-Rong 2
	2022
发表期刊	IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
ISSN	2329-9290
卷号	30 页码:721-733
摘要	Projecting the input text pair into a common semantic space where the matching function can be readily learned is an essential step for asymmetrical text matching. In the practice, it is often observed that the feature vectors from asymmetrical texts show a tendency to be gradually undistinguishable in the semantic space as the model is trained. However, the phenomenon is overlooked in existing studies. As a result, the feature vectors are constructed without any regularization, which inevitably hinders the learning of the downstream matching functions. In this paper, we first exploit the phenomenon and propose DDR-Match, a novel matching framework tailored for asymmetrical text matching. Specifically, in DDR-Match, a distribution distance-based regularizer is devised to accelerate the fusion of sequence representations corresponding to different domains in the semantic space. Then, we provide three instances of DDR-Match and make a comparison among them. DDR-Match is compatible with existing text matching methods by incorporating them as the underlying matching model. Four popular text matching methods are exploited in the paper. Extensive experimental results based on five publicly available benchmarks showed that DDR-Match consistently outperformed its underlying methods.
关键词	Semantics Neural networks Training Task analysis Measurement Speech processing Electronic mail Text matching sequence representation natural language processing
DOI	10.1109/TASLP.2022.3145289
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2019YFE0198200] ; National Natural Science Foundation of China[61872338] ; National Natural Science Foundation of China[61832017] ; National Natural Science Foundation of China[62006234] ; Beijing Outstanding Young Scientist Program[BJJWZYJH012019100020098] ; Intelligent Social Governance Interdisciplinary Platform, Major Innovation & Planning Interdisciplinary Platform for the Double-First Class Initiative, Renmin University of China ; Public Policy and Decision-making Research Lab of Renmin University of China
WOS研究方向	Acoustics ; Engineering
WOS类目	Acoustics ; Engineering, Electrical & Electronic
WOS记录号	WOS:000753551800007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18995
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xu, Jun
作者单位	1.Renmin Univ China, Sch Informat, Beijing 100872, Peoples R China 2.Renmin Univ China, Gaoling Sch Artificial Intelligence, Beijing Key Lab Big Data Management & Anal Method, Beijing 100872, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yu, Weijie,Xu, Chen,Xu, Jun,et al. Distribution Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2022,30:721-733.
APA	Yu, Weijie,Xu, Chen,Xu, Jun,Pang, Liang,&Wen, Ji-Rong.(2022).Distribution Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,30,721-733.
MLA	Yu, Weijie,et al."Distribution Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 30(2022):721-733.