Multi-turn Dialogue Generation Model with Dialogue Structure
Author:
Affiliation:

Clc Number:

TP391

Fund Project:

the National Natural Science Foundation of China (No. 61806137, No. 61702149).

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Recent research on multi-turn dialogue generation has focused on RNN or Transformer-based encoder-decoder architecture. However, most of these models ignore the influence of dialogue structure on dialogue generation. To solve this problem, this study proposes to use graph neural network structure to model the dialogue structure information, thus effectively describing the complex logic within a dialogue. Text-based similarity relation structure, turn-switching-based relation structure, and speaker-based relation structure are proposed for dialogue generation, and graph neural network is employed to realize information transmission and iteration in dialogue context. Extensive experiments on the DailyDialog dataset show that the proposed model consistently outperforms other baseline models in many indexes, which indicates that the proposed model with graph neural network can effectively describe various correlation structures in dialogue, thus contributing to the high-quality dialogue response generation.

    Reference
    Related
    Cited by
Get Citation

姜晓彤,王中卿,李寿山,周国栋.基于对话结构的多轮对话生成模型.软件学报,2022,33(11):4239-4250

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:November 12,2020
  • Revised:February 28,2021
  • Adopted:
  • Online: April 21,2021
  • Published: November 06,2022
You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063