Multi-turn Dialogue Generation Model with Dialogue Structure

被引：0
|
作者：
Jiang X.-T. [1 ]
Wang Z.-Q. [1 ]
Li S.-S. [1 ]
Zhou G.-D. [1 ]
机构：
[1] School of Computer Science and Technology, Soochow University, Suzhou
来源：
Ruan Jian Xue Bao/Journal of Software | 2022年 / 33卷 / 11期
关键词：
dialogue generation; dialogue structure; graph neural network; human-machine dialogue;
D O I：
10.13328/j.cnki.jos.006340
中图分类号：
学科分类号：
摘要：
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. © 2022 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：4239 / 4250
页数：11
相关论文
共 33 条
  • [1] Vinyals O, Le QV., A neural conversational model, (2015)
  • [2] Serban I, Sordoni A, Bengio Y, Courville A, Pineau J., Building end-to-end dialogue systems using generative hierarchical neural network models, Proc. of the AAAI Conf. on Artificial Intelligence, (2016)
  • [3] Serban I, Sordoni A, Lowe R, Charlin L, Pineau J, Courville A, Bengio Y., A hierarchical latent variable encoder-decoder model for generating dialogues, Proc. of the AAAI Conf. on Artificial Intelligence, (2017)
  • [4] Chen H, Ren Z, Tang J, Zhao YE, Yin D., Hierarchical variational memory network for dialogue generation, Proc. of the World Wide Web Conf, pp. 1653-1662, (2018)
  • [5] Zeng M, Wang Y, Luo Y., Dirichlet latent variable hierarchical recurrent encoder-decoder in dialogue generation, Proc. of the Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing (EMNLP-IJCNLP), pp. 1267-1272, (2019)
  • [6] Gu X, Cho K, Ha JW, Kim S., Dialogwae: Multimodal response generation with conditional Wasserstein auto-encoder, Proc. of the 7th Int’l Conf. of Learning Represtations, (2019)
  • [7] Xing C, Wu Y, Wu W, Huang Y, Zhou M., Hierarchical recurrent attention network for response generation, Proc. of the AAAI Conf. on Artificial Intelligence, (2018)
  • [8] Zhang H, Lan Y, Pang L, Guo J, Cheng X., ReCoSa: Detecting the relevant contexts with self-attention for multi-turn dialogue generation, Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3721-3730, (2019)
  • [9] Wang XP., The power relationship between Q & A and women in TV interview, Journal of Dezhou University, 26, 3, (2010)
  • [10] Chen H, Liu X, Yin D, Tang J., A survey on dialogue systems: recent advances and new frontiers, ACM SIGKDD Explorations Newsletter, 19, 2, (2017)
1234