Learning to Express in Knowledge-Grounded Conversation

被引:0
|
作者
Zhao, Xueliang [1 ,2 ]
Fu, Tingchen [3 ]
Tao, Chongyang [4 ]
Wu, Wei [5 ]
Zhao, Dongyan [1 ,2 ]
Yan, Rui [3 ]
机构
[1] Peking Univ, Wangxuan Inst Comp Technol, Beijing, Peoples R China
[2] Peking Univ, Ctr Data Sci, AAIS, Beijing, Peoples R China
[3] Renmin Univ China, Gaoling Sch Artificial Intelligence, Beijing, Peoples R China
[4] Microsoft, Beijing, Peoples R China
[5] Meituan, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a response with proper knowledge, yet neglect that the same knowledge could be expressed differently by speakers even under the same context. In this work, we mainly consider two aspects of knowledge expression, namely the structure of the response and style of the content in each part. We therefore introduce two sequential latent variables to represent the structure and the content style respectively. We propose a segmentation-based generation model and optimize the model by a variational approach to discover the underlying pattern of knowledge expression in a response. Evaluation results on two benchmarks indicate that our model can learn the structure style defined by a few examples and generate responses in desired content style.
引用
收藏
页码:2258 / 2273
页数:16
相关论文
共 50 条
  • [1] A Knowledge-Grounded Neural Conversation Model
    Ghazvininejad, Marjan
    Brockett, Chris
    Chang, Ming-Wei
    Dolan, Bill
    Gao, Jianfeng
    Yih, Wen-tau
    Galley, Michel
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 5110 - 5117
  • [2] Deliberation Selector for Knowledge-Grounded Conversation Generation
    Zhao, Huan
    Wang, Yiqing
    Li, Bo
    Wang, Song
    Zhang, Zixing
    Zha, Xupeng
    PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT III, 2022, 13631 : 226 - 239
  • [3] DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation
    Meng, Chuan
    Ren, Pengjie
    Chen, Zhumin
    Sun, Weiwei
    Ren, Zhaochun
    Tu, Zhaopeng
    de Rijke, Maarten
    PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20), 2020, : 1151 - 1160
  • [4] Exploiting Text Matching Techniques for Knowledge-Grounded Conversation
    Ahn, Yeonchan
    Lee, Sang-Goo
    Park, Jaehui
    IEEE ACCESS, 2020, 8 : 126201 - 126214
  • [5] EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning
    Zhou, Hao
    Huang, Minlie
    Liu, Yong
    Chen, Wei
    Zhu, Xiaoyan
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 2383 - 2395
  • [6] Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation
    Cui, Fuwei
    Di, Hui
    Ren, Hongjie
    Ouchi, Kazushige
    Liu, Ze
    Xu, Jinan
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 4620 - 4630
  • [7] Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
    Zheng, Chujie
    Cao, Yunbo
    Jiang, Daxin
    Huang, Minlie
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 115 - 125
  • [8] CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
    Ghaddar, Abbas
    Alfonso-Hermelo, David
    Langlais, Philippe
    Rezagholizadeh, Mehdi
    Chen, Boxing
    Parthasarathi, Prasanna
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, 2024, : 1534 - 1551
  • [9] Retrieval-Augmented Response Generation for Knowledge-Grounded Conversation in the Wild
    Ahn, Yeonchan
    Lee, Sang-Goo
    Shim, Junho
    Park, Jaehui
    IEEE ACCESS, 2022, 10 : 131374 - 131385
  • [10] KSRL: Knowledge Selection Based Reinforcement Learning for Knowledge-Grounded Dialogue
    Ma, Zhanyu
    Ye, Jian
    Cheng, Shuang
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT IV, KSEM 2023, 2023, 14120 : 189 - 196