mlsanityData to 14 Oct 2026

Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking

arXiv 2105.04222 ↗First posted 10 May 2021cs.CLcited by 61

Not on the map. Why?

Abstract (arXiv)

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes dialogue context and slots with a pre-trained self-attentive encoder, and generates slot values in an auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information across slots to facilitate cross-domain knowledge transfer. Experimental results on the MultiWOZ dataset show that our proposed method significantly improves existing state-of-the-art results in the zero-shot cross-domain setting.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 25 of its 31 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

25 of 31 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2018Self-Attention with Relative Position Representationscited by 1,120
  4. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  5. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  6. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  7. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  8. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 204
  9. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  10. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  11. 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
  12. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
13 more
  1. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  2. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  3. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  4. 2019Dialog State Tracking: A Neural Reading Comprehension Approachcited by 62
  5. 2020CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackerscited by 43
  6. 2019Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systemscited by 42
  7. 2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
  8. 2017Towards Zero-Shot Frame Semantic Parsing for Domain Scalingcited by 40
  9. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  10. 2019Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answeringcited by 39
  11. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  12. 2020Language Model is All You Need: Natural Language Understanding as Question Answeringcited by 29
  13. 2021Slot Self-Attentive Dialogue State Trackingcited by 27

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 19; 2023: 19; 2024: 12; 2025: 3.

61 papers.

Sort:

By area:

  1. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  2. 2021Language Models are Few-shot Multilingual Learnerscited by 92
  3. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  4. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  5. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  6. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  7. 2022Continual Prompt Tuning for Dialog State Trackingcited by 44
  8. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  9. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
  10. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  11. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  12. 2023Towards LLM-driven Dialogue State Trackingcited by 25
38 more
  1. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  2. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  3. 2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
  4. 2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 19
  5. 2021Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systemscited by 18
  6. 2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingcited by 17
  7. 2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
  8. 2023Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systemscited by 16
  9. 2023A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptionscited by 15
  10. 2022Workflow Discovery from Dialogues in the Low Data Regimecited by 12
  11. 2021Style Control for Schema-Guided Natural Language Generationcited by 10
  12. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  13. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  14. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  15. 2022Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systemscited by 9
  16. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
  17. 2022A Dual Prompt Learning Framework for Few-Shot Dialogue State Trackingcited by 8
  18. 2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
  19. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
  20. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  21. 2022ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Modelscited by 6
  22. 2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
  23. 2022Instilling Type Knowledge in Language Models via Multi-Task QAcited by 5
  24. 2022A Multi-Task BERT Model for Schema-Guided Dialogue State Trackingcited by 5
  25. 2023Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Trackingcited by 5
  26. 2023Continual Dialogue State Tracking via Example-Guided Question Answeringcited by 4
  27. 2023A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systemscited by 4
  28. 2024Confidence Estimation for LLM-Based Dialogue State Trackingcited by 4
  29. 2022MetaASSIST: Robust Dialogue State Tracking with Meta Learningcited by 3
  30. 2023Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schemacited by 3
  31. 2023Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuningcited by 3
  32. 2023Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Datacited by 3
  33. 2022XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Trackingcited by 2
  34. 2023A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correctioncited by 2
  35. 2024Enhancing Depression-Diagnosis-Oriented Chat with Psychological State Trackingcited by 2
  36. 2024A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understandingcited by 2
  37. 2023Multilingual Few-Shot Learning via Language Model Retrievalcited by 1
  38. 2023Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turnscited by 1

50 most cited of 61 All 61 (JSON)