中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 自然语言处理
Heterogeneous Relational Graph Neural Networks with Adaptive Objective for End-to-End Task-Oriented Dialogue

文献类型：期刊论文

作者Liu, Qingbin1,2; Bai, Guirong1,2; He, Shizhu1,2; Liu, Cao3; Liu, Kang1,2; Zhao, Jun1,2
刊名KNOWLEDGE-BASED SYSTEMS
出版日期2021-09-05
卷号227页码:12
ISSN号0950-7051
关键词End-to-end task-oriented dialogue Heterogeneous relational graph neural networks Shared-private parameterization Hierarchical attention mechanism Adaptive objective
DOI10.1016/j.knosys.2021.107186
通讯作者Zhao, Jun(jzhao@nlpr.ia.ac.cn)
英文摘要End-to-end task-oriented dialogue systems, which provide a natural and informative way for human- computer interaction, are gaining more and more attention. The main challenge of such dialogue systems is how to effectively incorporate external knowledge bases into the learning framework. However, existing approaches usually overlook the natural graph structure information in the knowledge base and the relevant information between the knowledge base and the dialogue history, which makes them deficient in handling the above challenge. Besides, existing methods ignore the entity imbalance problem and treat different entities in system responses indiscriminately, which limits the learning of hard target entities. To address the two challenges, we propose Heterogeneous Relational Graph Neural Networks with Adaptive Objective (HRGNN-AO) for end-to-end task-oriented dialogue systems. In the method, we explore effective heterogeneous relational graphs to jointly capture multi perspective graph structure information from the knowledge base and the dialogue history, which ultimately facilitates the generation of informative responses. Moreover, we design two components, shared-private parameterization and hierarchical attention mechanism, to solve the overfitting and confusion problems in the heterogeneous relational graph, respectively. To handle the entity imbalance problem, we propose an adaptive objective, which dynamically adjusts the weights of different target entities during the training process. The experimental results show that HRGNN-AO is effective in generating informative responses and outperforms state-of-the-art dialogue systems on the SMD and extended Multi-WOZ 2.1 datasets. (c) 2021 Elsevier B.V. All rights reserved.
资助项目National Key Research and Development Program of China[2020AAA0106400] ; National Natural Science Foundation of China[61922085] ; National Natural Science Foundation of China[61976211] ; Beijing Academy of Artificial Intelligence[BAAI2019QN0301] ; Key Research Program of the Chinese Academy of Sciences[ZDBS-SSW-JSC006] ; National Laboratory of Pattern Recognition, China ; Youth Innovation Promotion Association CAS, China ; Meituan-Dianping Group
WOS研究方向Computer Science
语种英语
出版者ELSEVIER
WOS记录号WOS:000679379400017
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Academy of Artificial Intelligence ; Key Research Program of the Chinese Academy of Sciences ; National Laboratory of Pattern Recognition, China ; Youth Innovation Promotion Association CAS, China ; Meituan-Dianping Group
源URL[http://ir.ia.ac.cn/handle/173211/45581]  
专题模式识别国家重点实验室_自然语言处理
通讯作者Zhao, Jun
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
3.Meituan, Beijing 100102, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Qingbin,Bai, Guirong,He, Shizhu,et al. Heterogeneous Relational Graph Neural Networks with Adaptive Objective for End-to-End Task-Oriented Dialogue[J]. KNOWLEDGE-BASED SYSTEMS,2021,227:12.
APA Liu, Qingbin,Bai, Guirong,He, Shizhu,Liu, Cao,Liu, Kang,&Zhao, Jun.(2021).Heterogeneous Relational Graph Neural Networks with Adaptive Objective for End-to-End Task-Oriented Dialogue.KNOWLEDGE-BASED SYSTEMS,227,12.
MLA Liu, Qingbin,et al."Heterogeneous Relational Graph Neural Networks with Adaptive Objective for End-to-End Task-Oriented Dialogue".KNOWLEDGE-BASED SYSTEMS 227(2021):12.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。