mlsanityData to 14 Oct 2026

A Network-based End-to-End Trainable Task-oriented Dialogue System

arXiv 1604.04562 ↗First posted 15 Apr 2016cs.CL cs.AI cs.NEcited by 252

Not on the map. Why?

Abstract (arXiv)

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

Key facts. Cited by 252 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 74; 2022: 73; 2023: 42; 2024: 36; 2025: 18; 2026: 7.

252 papers.

Sort:

By area:

  1. 2021Ethical and social risks of harm from Language Modelscited by 966
  2. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  3. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 148
  4. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  5. 2023MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problemscited by 131
  6. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  7. 2021KLUE: Korean Language Understanding Evaluationcited by 114
  8. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  9. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 88
  10. 2023SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agentscited by 71
  11. 2022Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Supportcited by 68
  12. 2022Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agentscited by 62
38 more
  1. 2022In conversation with Artificial Intelligence: aligning language models with human valuescited by 62
  2. 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 56
  3. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  4. 2021Multilingual Autoregressive Entity Linkingcited by 50
  5. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  6. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  7. 2024Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulatorcited by 39
  8. 2021Transferable Dialogue Systems and User Simulatorscited by 36
  9. 2021Multilingual and Cross-Lingual Intent Detection from Spoken Datacited by 35
  10. 2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
  11. 2021Communicating Natural Programs to Humans and Machinescited by 35
  12. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  13. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  14. 2023Opportunities and Challenges in Neural Dialog Tutoringcited by 33
  15. 2024SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generationcited by 33
  16. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
  17. 2021Conversational Question Answering: A Surveycited by 31
  18. 2021GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systemscited by 31
  19. 2021Semi-Supervised Variational Reasoning for Medical Dialogue Generationcited by 30
  20. 2021Annotation Inconsistency and Entity Bias in MultiWOZcited by 30
  21. 2021"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversationscited by 30
  22. 2022Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialogcited by 30
  23. 2022Visualize Before You Write: Imagination-Guided Open-Ended Text Generationcited by 30
  24. 2021Slot Self-Attentive Dialogue State Trackingcited by 27
  25. 2022INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactionscited by 27
  26. 2021DeliData: A dataset for deliberation in multi-party problem solvingcited by 26
  27. 2021Semantic Representation for Dialogue Modelingcited by 24
  28. 2024DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialoguescited by 24
  29. 2021Pretraining the Noisy Channel Model for Task-Oriented Dialoguecited by 23
  30. 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
  31. 2025LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Modelscited by 23
  32. 2021Learning Neural Templates for Recommender Dialogue Systemcited by 22
  33. 2024MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotationscited by 22
  34. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learningcited by 21
  35. 2021DS-TOD: Efficient Domain Specialization for Task Oriented Dialogcited by 21
  36. 2021Amendable Generation for Dialogue State Trackingcited by 21
  37. 2021Effective Sequence-to-Sequence Dialogue State Trackingcited by 20
  38. 2021ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialoguescited by 20

50 most cited of 252 All 252 (JSON)