Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking

被引:0
|
作者
Feng, Yue [1 ]
Lipani, Aldo [1 ]
Ye, Fanghua [1 ]
Zhang, Qiang [2 ]
Yilmaz, Emine [1 ]
机构
[1] UCL, London, England
[2] Zhejiang Univ, Hangzhou, Peoples R China
来源
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS) | 2022年
基金
英国工程与自然科学研究理事会;
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
Dialogue State Tracking (DST) aims to keep track of users' intentions during the course of a conversation. In DST, modelling the relations among domains and slots is still an under-studied problem. Existing approaches that have considered such relations generally fall short in: (1) fusing prior slot-domain membership relations and dialogue-aware dynamic slot relations explicitly, and (2) generalizing to unseen domains. To address these issues, we propose a novel Dynamic Schema Graph Fusion Network (DSGFNet), which generates a dynamic schema graph to explicitly fuse the prior slot-domain membership relations and dialogue-aware dynamic slot relations. It also uses the schemata to facilitate knowledge transfer to new domains. DSGFNet consists of a dialogue utterance encoder, a schema graph encoder, a dialogue-aware schema graph evolving network, and a schema graph enhanced dialogue state decoder. Empirical results on benchmark datasets (i.e., SGD, MultiWOZ2.1, and MultiWOZ2.2), show that DSGFNet outperforms existing methods.
引用
收藏
页码:115 / 126
页数:12
相关论文
共 50 条
  • [21] XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking
    Zhou, Han
    Iacobacci, Ignacio
    Minervini, Pasquale
    17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 999 - 1009
  • [22] MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
    Eric, Mihail
    Goel, Rahul
    Paul, Shachi
    Kumar, Adarsh
    Sethi, Abhishek
    Goyal, Anuj Kumar
    Ku, Peter
    Agarwal, Sanchit
    Gao, Shuyang
    Hakkani-Tur, Dilek
    PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), 2020, : 422 - 428
  • [23] Domain-Aware Dialogue State Tracker for Multi-Domain Dialogue Systems
    Balaraman, Vevake
    Magnini, Bernardo
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 : 866 - 873
  • [24] A Stack-Propagation Framework With Slot Filling for Multi-Domain Dialogue State Tracking
    Wang, Yufan
    He, Tingting
    Mei, Jie
    Fan, Rui
    Tu, Xinhui
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (01) : 1240 - 1254
  • [25] MULTI-STEP DIALOGUE STATE TRACKER WITH SCHEMA-GUIDED GRAPH CONVOLUTIONAL NETWORK
    Zhang, Xuejun
    Zhang, Pengyuan
    Yan, Yonghong
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2021, 17 (06): : 1955 - 1971
  • [26] Multi-domain fusion deep graph convolution neural network for EEG emotion recognition
    Bi, Jinying
    Wang, Fei
    Yan, Xin
    Ping, Jingyu
    Wen, Yongzhao
    Neural Computing and Applications, 2022, 34 (24): : 22241 - 22255
  • [27] Multi-domain fusion deep graph convolution neural network for EEG emotion recognition
    Bi, Jinying
    Wang, Fei
    Yan, Xin
    Ping, Jingyu
    Wen, Yongzhao
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (24): : 22241 - 22255
  • [28] Multi-domain fusion deep graph convolution neural network for EEG emotion recognition
    Jinying Bi
    Fei Wang
    Xin Yan
    Jingyu Ping
    Yongzhao Wen
    Neural Computing and Applications, 2022, 34 : 22241 - 22255
  • [29] Multi-Domain Fusion Graph Network for Semi-Supervised PolSAR Image Classification
    Tang, Rui
    Pu, Fangling
    Yang, Rui
    Xu, Zhaozhuo
    Xu, Xin
    REMOTE SENSING, 2023, 15 (01)
  • [30] Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
    Su, Ruolin
    Wu, Ting-Wei
    Juang, Biing-Hwang
    INTERSPEECH 2021, 2021, : 236 - 240