Transfer Hierarchical Attention Network for Generative Dialog System

doi:10.1007/s11633-019-1200-0

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Transfer Hierarchical Attention Network for Generative Dialog System
	Xiang Zhang; Qiang Yang
发表期刊	International Journal of Automation and Computing
ISSN	1476-8186
	2019
卷号	16 期号:6 页码:720-736
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.
关键词	Dialog system transfer learning deep learning natural language processing (NLP) artificial intelligence.
DOI	10.1007/s11633-019-1200-0
引用统计	被引频次：9[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42370
专题	学术期刊_Machine Intelligence Research
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.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
IJAC-2019-06-129.pdf（1145KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载