Recent advances and challenges in task-oriented dialog systems

被引：0
|
作者：
Zheng Zhang
Ryuichi Takanobu
Qi Zhu
MinLie Huang
XiaoYan Zhu
机构：
[1] Tsinghua University,Department of Computer Science & Technology
[2] Tsinghua University (THUAI),Institute for Artificial Intelligence
[3] Beijing National Research Center for Information Science & Technology,undefined
来源：
Science China Technological Sciences | 2020年 / 63卷
关键词：
task-oriented dialog systems; natural language understanding; dialog policy; dialog state tracking; natural language generation;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities. In this paper, we survey recent advances and challenges in task-oriented dialog systems. We also discuss three critical topics for task-oriented dialog systems: (1) improving data efficiency to facilitate dialog modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance, and (3) integrating domain ontology knowledge into the dialog model. Besides, we review the recent progresses in dialog evaluation and some widely-used corpora. We believe that this survey, though incomplete, can shed a light on future research in task-oriented dialog systems.
引用
收藏
页码：2011 / 2027
页数：16
相关论文
共 50 条
  • [41] Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function
    Siddique, A. B.
    Maqbool, M. H.
    Taywade, Kshitija
    Foroosh, Hassan
    [J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 1787 - 1797
  • [42] Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
    Liu, Hong
    Cai, Yucheng
    Lin, Zhenru
    Ou, Zhijian
    Huang, Yi
    Feng, Junlan
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 31 : 970 - 984
  • [43] SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations
    Kottur, Satwik
    Moon, Seungwhan
    Geramifard, Alborz
    Damavandi, Babak
    [J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 4903 - 4912
  • [44] Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog
    Mishra, Mayank
    Contractor, Danish
    Raghu, Dinesh
    [J]. 17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1778 - 1787
  • [45] Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog
    Pasupae, Panupong
    Gupta, Sonal
    Mandyam, Karishma
    Shah, Rushin
    Lewis, Mike
    Zettlemoyer, Luke
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 1520 - 1526
  • [46] An empirical assessment of deep learning approaches to task-oriented dialog management
    Mateju, Lukas
    Griol, David
    Callejas, Zoraida
    Molina, Jose Manuel
    Sanchis, Araceli
    [J]. NEUROCOMPUTING, 2021, 439 : 327 - 339
  • [47] Combining Open Domain Question Answering with a Task-Oriented Dialog System
    Nehring, Jan
    Feldhus, Nils
    Ahmed, Akhyar
    Kaur, Harleen
    [J]. 1ST WORKSHOP ON DOCUMENT-GROUNDED DIALOGUE AND CONVERSATIONAL QUESTION ANSWERING (DIALDOC 2021), 2021, : 38 - 45
  • [48] Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
    Zhang, Jiaping
    Zhao, Tiancheng
    Yu, Zhou
    [J]. 19TH ANNUAL MEETING OF THE SPECIAL INTEREST GROUP ON DISCOURSE AND DIALOGUE (SIGDIAL 2018), 2018, : 140 - 150
  • [49] Few-shot Natural Language Generation for Task-Oriented Dialog
    Peng, Baolin
    Zhu, Chenguang
    Li, Chunyuan
    Li, Xiujun
    Li, Jinchao
    Zeng, Michael
    Gao, Jianfeng
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 172 - 182
  • [50] DS-TOD: Efficient Domain Specialization for Task-Oriented Dialog
    Hung, Chia-Chien
    Lauscher, Anne
    Ponzetto, Simone Paolo
    Glavas, Goran
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), 2022, : 891 - 904
12345