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
  • [31] Knowledge-Grounded Target Group Language Recognition in Hate Speech
    Reyero Lobo, Paula
    Daga, Enrico
    Alani, Harith
    Fernandez, Miriam
    KNOWLEDGE GRAPHS: SEMANTICS, MACHINE LEARNING, AND LANGUAGES, 2023, 56 : 1 - 18
  • [32] Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue
    Yang, Yizhe
    Huang, Heyan
    Liu, Yuhang
    Gao, Yang
    2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2023), 2023, : 15846 - 15858
  • [33] Knowledge-Grounded Dialogue Flow Management for Social Robots and Conversational Agents
    Grassi, Lucrezia
    Recchiuto, Carmine Tommaso
    Sgorbissa, Antonio
    INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS, 2022, 14 (05) : 1273 - 1293
  • [34] KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models
    Yu, Zhuohao
    Gao, Chang
    Yao, Wenjin
    Wang, Yidong
    Ye, Wei
    Wang, Jindong
    Xie, Xing
    Zhang, Yue
    Zhang, Shikun
    PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 5967 - 5985
  • [35] Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues
    Wang, Hongru
    Deng, Yang
    Wang, Rui
    Mi, Fei
    Wang, Weichao
    Wang, Yasheng
    Kwanc, Wai-Chung
    King, Irwin
    Wong, Kam-Fai
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EMNLP 2023), 2023, : 9556 - 9569
  • [36] Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment
    Xue, Boyang
    Wang, Weichao
    Wang, Hongru
    Mi, Fei
    Wang, Rui
    Wang, Yasheng
    Shang, Lifeng
    Jiang, Xin
    Liu, Qun
    Wong, Kam-Fai
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS - EMNLP 2023, 2023, : 7829 - 7844
  • [37] Knowledge-Grounded Attention-Based Neural Machine Translation Model
    Israr, Huma
    Khan, Safdar Abbas
    Tahir, Muhammad Ali
    Shahzad, Muhammad Khuram
    Ahmad, Muneer
    Zain, Jasni Mohamad
    APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2025, 2025 (01)
  • [38] Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation
    Chen, Xiuyi
    Meng, Fandong
    Li, Peng
    Chen, Feilong
    Xu, Shuang
    Xu, Bo
    Zhou, Jie
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 3426 - 3437
  • [39] AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue
    Jung, Jaehun
    Son, Bokyung
    Lyu, Sungwon
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 3484 - 3497
  • [40] Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters
    Xu, Yan
    Ishii, Etsuko
    Cahyawijaya, Samuel
    Liu, Zihan
    Winata, Genta Indra
    Madotto, Andrea
    Su, Dan
    Fung, Pascale
    PROCEEDINGS OF THE SECOND DIALDOC WORKSHOP ON DOCUMENT-GROUNDED DIALOGUE AND CONVERSATIONAL QUESTION ANSWERING (DIALDOC 2022), 2022, : 93 - 107