mlsanityData to 7 Oct 2026

Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog

arXiv 2210.08917 ↗First posted 17 Oct 2022cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Traditional end-to-end task-oriented dialog systems first convert dialog context into belief state and action state before generating the system response. The system response performance is significantly affected by the quality of the belief state and action state. We first explore what dialog context representation is beneficial to improving the quality of the belief state and action state, which further enhances the generated response quality. To tackle our exploration, we propose Mars, an end-to-end task-oriented dialog system with two contrastive learning strategies to model the relationship between dialog context and belief/action state representations. Empirical results show dialog context representations, which are more different from semantic state representations, are more conducive to multi-turn task-oriented dialog. Moreover, our proposed Mars achieves state-of-the-art performance on the MultiWOZ 2.0, CamRest676, and CrossWOZ.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

33 of 59 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  9. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  10. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  11. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  12. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
21 more
  1. 2020DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representationscited by 249
  2. 2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
  3. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  4. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  5. 2020CLEAR: Contrastive Learning for Sentence Representationcited by 186
  6. 2020CERT: Contrastive Self-supervised Learning for Language Understandingcited by 169
  7. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  8. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  9. 2020UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2cited by 111
  10. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  11. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  12. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  13. 2020CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Datasetcited by 66
  14. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  15. 2019UER: An Open-Source Toolkit for Pre-training Modelscited by 61
  16. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  17. 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
  18. 2019Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialogcited by 37
  19. 2022BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialogcited by 20
  20. 2021Domain State Tracking for a Simplified Dialogue Systemcited by 17
  21. 2021Contextual Semantic Parsing for Multilingual Task-Oriented Dialoguescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 5; 2026: 2.

11 papers.

  1. 2024MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotationscited by 21
  2. 2023Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goalscited by 8
  3. 2025Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategycited by 3
  4. 2024TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Samplingcited by 1
  5. 2024Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systemscited by 1
  6. 2025CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignmentcited by 1
  7. 2026One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systemscited by 1
  8. 2025Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systemscited by 0
  9. 2025Collaborative and Proactive Management of Task-Oriented Conversationscited by 0
  10. 2025MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversationscited by 0
  11. 2026Extracting Training Dialogue Data from Large Language Model based Task Botscited by 0