mlsanityData to 7 Oct 2026

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions

arXiv 2311.09008 ↗First posted 15 Nov 2023cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of large pre-trained models, has further led to significant progress in EToD research in recent years. In this paper, we present a thorough review and provide a unified perspective to summarize existing approaches as well as recent trends to advance the development of EToD research. The contributions of this paper can be summarized: (1) textbftextitFirst survey: to our knowledge, we take the first step to present a thorough survey of this research field; (2) textbftextitNew taxonomy: we first introduce a unified perspective for EToD, including (i) textitModularly EToD and (ii) textitFully EToD; (3) textbftextitNew Frontiers: we discuss some potential frontier areas as well as the corresponding challenges, hoping to spur breakthrough research in EToD field; (4) textbftextitAbundant resources: we build a public websitefootnoteWe collect the related papers, baseline projects, and leaderboards for the community at urlhttps://etods.net/., where EToD researchers could directly access the recent progress. We hope this work can serve as a thorough reference for the EToD research community.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 74 of its 106 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

74 of 106 references.

References · 74

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  5. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  6. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  8. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  9. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  10. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  11. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  12. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
38 more
  1. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
  4. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  5. 2019A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understandingcited by 106
  6. 2016Learning End-to-End Goal-Oriented Dialogcited by 104
  7. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  8. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  9. 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
  10. 2020Recent Advances and Challenges in Task-oriented Dialog Systemcited by 78
  11. 2018Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systemscited by 70
  12. 2020A Co-Interactive Transformer for Joint Slot Filling and Intent Detectioncited by 61
  13. 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 55
  14. 2021SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversationscited by 54
  15. 2018Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systemscited by 53
  16. 2019Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Modelscited by 53
  17. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  18. 2017End-to-End Task-Completion Neural Dialogue Systemscited by 52
  19. 2020Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Surveycited by 51
  20. 2022GODEL: Large-Scale Pre-Training for Goal-Directed Dialogcited by 50
  21. 2019Global-to-local Memory Pointer Networks for Task-Oriented Dialoguecited by 47
  22. 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
  23. 2019Structured Fusion Networks for Dialogcited by 40
  24. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  25. 2020Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialogcited by 37
  26. 2016Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Accesscited by 36
  27. 2020Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systemscited by 35
  28. 2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
  29. 2017Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learningcited by 31
  30. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
  31. 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
  32. 2020LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimizationcited by 30
  33. 2021GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systemscited by 30
  34. 2022A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learningcited by 30
  35. 2016Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learningcited by 29
  36. 2020GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systemscited by 29
  37. 2020Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue Systemcited by 28
  38. 2019A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directionscited by 26

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 6.

17 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  3. 2025OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarioscited by 9
  4. 2025DiMA: An LLM-Powered Ride-Hailing Assistant at DiDicited by 7
  5. 2024Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Modelscited by 6
  6. 2024Opportunities and Challenges of Generative-AI in Financecited by 6
  7. 2025Spoken Conversational Agents with Large Language Modelscited by 4
  8. 2026STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generationcited by 3
  9. 2025CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignmentcited by 1
  10. 2026AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agentscited by 1
  11. 2026Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Frameworkcited by 1
  12. 2025Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialoguescited by 0
5 more
  1. 2025DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systemscited by 0
  2. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0
  3. 2026TRACER: Early Failure Detection for Task-Oriented Dialoguecited by 0
  4. 2026An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestrationcited by 0
  5. 2026Large-Scale User Behavior Analysis in Multimodal AI-Assisted Manual Task Executioncited by 0