mlsanityData to 7 Oct 2026

Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking

arXiv 2203.01552 ↗First posted 3 Mar 2022cs.CL cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

Annotating task-oriented dialogues is notorious for the expensive and difficult data collection process. Few-shot dialogue state tracking (DST) is a realistic solution to this problem. In this paper, we hypothesize that dialogue summaries are essentially unstructured dialogue states; hence, we propose to reformulate dialogue state tracking as a dialogue summarization problem. To elaborate, we train a text-to-text language model with synthetic template-based dialogue summaries, generated by a set of rules from the dialogue states. Then, the dialogue states can be recovered by inversely applying the summary generation rules. We empirically show that our method DS2 outperforms previous works on few-shot DST in MultiWoZ 2.0 and 2.1, in both cross-domain and multi-domain settings. Our method also exhibits vast speedup during both training and inference as it can generate all states at once. Finally, based on our analysis, we discover that the naturalness of the summary templates plays a key role for successful training.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 53 of its 73 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

53 of 73 references.

References · 53

  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. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  6. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  7. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  8. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  9. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  10. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  11. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  12. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
38 more
  1. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  2. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  3. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  4. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  5. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  6. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  7. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  8. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  9. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  10. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  11. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  12. 2021KLUE: Korean Language Understanding Evaluationcited by 113
  13. 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
  14. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  15. 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
  16. 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
  17. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  18. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  19. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  20. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  21. 2020Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarizationcited by 72
  22. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  23. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  24. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  25. 2019Dialog State Tracking: A Neural Reading Comprehension Approachcited by 62
  26. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  27. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  28. 2020MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotationcited by 51
  29. 2021Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarizationcited by 46
  30. 2020CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackerscited by 43
  31. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  32. 2019Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answeringcited by 39
  33. 2021ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Miningcited by 37
  34. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  35. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  36. 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
  37. 2021EmailSum: Abstractive Email Thread Summarizationcited by 24
  38. 2019Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generationcited by 21

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 8; 2024: 4; 2025: 1; 2026: 1.

21 papers.

Sort:

By area:

  1. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  2. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  3. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  4. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  5. 2023In-Context Learning User Simulators for Task-Oriented Dialog Systemscited by 19
  6. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  7. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  8. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
  9. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  10. 2023S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMscited by 7
  11. 2022DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarizationcited by 6
  12. 2023Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Trackingcited by 6
9 more
  1. 2022MetaASSIST: Robust Dialogue State Tracking with Meta Learningcited by 3
  2. 2023Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuningcited by 3
  3. 2024Using Large Multimodal Models to Extract Knowledge Components for Knowledge Tracing from Multimedia Question Informationcited by 2
  4. 2025AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agentscited by 2
  5. 2022CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Trackingcited by 1
  6. 2023UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Trackingcited by 1
  7. 2024Intent-driven In-context Learning for Few-shot Dialogue State Trackingcited by 1
  8. 2024State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Trackingcited by 0
  9. 2026Dynamic Knowledge Fusion for Multi-Domain Dialogue State Trackingcited by 0