CASIA OpenIR  > 综合信息系统研究中心  > 视知觉融合及其应用
SynDG: Syntax-aware Dialogue Generation
Junyan Qiu1,2; Yiping Yang3; Haitao Wang2
Conference NameInternational Conference on Computing and Artificial Intelligence
Conference DateMarch 17 - 20, 2023
Conference PlaceTianjin China

Dialogue system is designed to converse with humans in a natural way. As an essential part of dialogue system, dialogue generation aims to generate proper response given historical context. Recently, sequence-to-sequence (seq2seq) based models have achieved great success but suffer from ungrammatical problems. In this paper, we propose a Syntax-aware Dialogue Generation (SynDG) model that incorporates syntactic information to generate grammatical responses with an encoder-decoder framework. Specifically, we first construct a syntax-graph with a dependency parser on the dialogue corpus. Then, we employ three graph embedding algorithms to learn syntactic word representations as the input of seq2seq framework. Furthermore, we devise training strategies to predict syntactic structure of the sentence for sufficient syntax understanding. Our empirical study on two multi-turn dialogue datasets demonstrates the effectiveness of SynDG in generating natural and grammatical responses

Keyworddialogue system natural language generation dependency parsing graph attention network
MOST Discipline Catalogue工学::计算机科学与技术(可授工学、理学学位)
Indexed ByEI
IS Representative Paper
Sub direction classification自然语言处理
planning direction of the national heavy laboratory语音语言处理
Paper associated data
Document Type会议论文
Corresponding AuthorJunyan Qiu
Affiliation1.University of Chinese Academy of Sciences
2.Institute of Automation, Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Junyan Qiu,Yiping Yang,Haitao Wang. SynDG: Syntax-aware Dialogue Generation[C]:ACM,2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
syndg.pdf(903KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Junyan Qiu]'s Articles
[Yiping Yang]'s Articles
[Haitao Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Junyan Qiu]'s Articles
[Yiping Yang]'s Articles
[Haitao Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Junyan Qiu]'s Articles
[Yiping Yang]'s Articles
[Haitao Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: syndg.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.