Transfer Hierarchical Attention Network for Generative Dialog System

doi:10.1007/s11633-019-1200-0

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Transfer Hierarchical Attention Network for Generative Dialog System
	Xiang Zhang; Qiang Yang
刊名	International Journal of Automation and Computing
	2019
卷号	16 期号:6 页码:720-736
关键词	Dialog system transfer learning deep learning natural language processing (NLP) artificial intelligence.
ISSN号	1476-8186
DOI	10.1007/s11633-019-1200-0
英文摘要	In generative dialog systems, learning representations for the dialog context is a crucial step in generating high quality responses. The dialog systems are required to capture useful and compact information from mutually dependent sentences such that the generation process can effectively attend to the central semantics. Unfortunately, existing methods may not effectively identify importance distributions for each lower position when computing an upper level feature, which may lead to the loss of information critical to the constitution of the final context representations. To address this issue, we propose a transfer learning based method named transfer hierarchical attention network (THAN). The THAN model can leverage useful prior knowledge from two related auxiliary tasks, i.e., keyword extraction and sentence entailment, to facilitate the dialog representation learning for the main dialog generation task. During the transfer process, the syntactic structure and semantic relationship from the auxiliary tasks are distilled to enhance both the word-level and sentence-level attention mechanisms for the dialog system. Empirically, extensive experiments on the Twitter Dialog Corpus and the PERSONA-CHAT dataset demonstrate the effectiveness of the proposed THAN model compared with the state-of-the-art methods.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42370]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	Computer Science and Engineering Department, Hong Kong University of Science and Technology, Hong Kong 999077, China
推荐引用方式 GB/T 7714	Xiang Zhang,Qiang Yang. Transfer Hierarchical Attention Network for Generative Dialog System[J]. International Journal of Automation and Computing,2019,16(6):720-736.
APA	Xiang Zhang,&Qiang Yang.(2019).Transfer Hierarchical Attention Network for Generative Dialog System.International Journal of Automation and Computing,16(6),720-736.
MLA	Xiang Zhang,et al."Transfer Hierarchical Attention Network for Generative Dialog System".International Journal of Automation and Computing 16.6(2019):720-736.