mlsanityData to 14 Oct 2026

Description-Driven Task-Oriented Dialog Modeling

arXiv 2201.08904 ↗First posted 21 Jan 2022cs.CL cs.AIcited by 50

Not on the map. Why?

Abstract (arXiv)

Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks. Such information is conventionally specified in terms of intents and slots contained in task-specific ontology or schemata. Since these schemata are designed by system developers, the naming convention for slots and intents is not uniform across tasks, and may not convey their semantics effectively. This can lead to models memorizing arbitrary patterns in data, resulting in suboptimal performance and generalization. In this paper, we propose that schemata should be modified by replacing names or notations entirely with natural language descriptions. We show that a language description-driven system exhibits better understanding of task specifications, higher performance on state tracking, improved data efficiency, and effective zero-shot transfer to unseen tasks. Following this paradigm, we present a simple yet effective Description-Driven Dialog State Tracking (D3ST) model, which relies purely on schema descriptions and an "index-picking" mechanism. We demonstrate the superiority in quality, data efficiency and robustness of our approach as measured on the MultiWOZ (Budzianowski et al.,2018), SGD (Rastogi et al., 2020), and the recent SGD-X (Lee et al., 2021) benchmarks.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 21 Jan 2022.

Builds on

32 of 44 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  4. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  5. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  6. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  7. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
  8. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  9. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  10. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  11. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 204
  12. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
20 more
  1. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  2. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  3. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  4. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 88
  5. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  6. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  7. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  8. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  9. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  10. 2020MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotationcited by 51
  11. 2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
  12. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  13. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  14. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
  15. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  16. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  17. 2020Language Model is All You Need: Natural Language Understanding as Question Answeringcited by 29
  18. 2019An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classificationcited by 20
  19. 2021Effective Sequence-to-Sequence Dialogue State Trackingcited by 20
  20. 2020Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Trackingcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 18; 2024: 19; 2025: 3; 2026: 2.

50 papers.

Sort:

By area:

  1. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  2. 2024Large Language Models Meet NLP: A Surveycited by 103
  3. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  4. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  5. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  6. 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
  7. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  8. 2023Towards LLM-driven Dialogue State Trackingcited by 25
  9. 2024Reliable LLM-based User Simulator for Task-Oriented Dialogue Systemscited by 25
  10. 2024Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulationcited by 24
  11. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  12. 2024MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotationscited by 22
38 more
  1. 2024Retrieval Augmented End-to-End Spoken Dialog Modelscited by 20
  2. 2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
  3. 2022Workflow Discovery from Dialogues in the Low Data Regimecited by 12
  4. 2022Speech Aware Dialog System Technology Challenge (DSTC11)cited by 10
  5. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  6. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  7. 2023Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understandingcited by 9
  8. 2025Human vs. Agent in Task-Oriented Conversationscited by 9
  9. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
  10. 2023Improved Instruction Ordering in Recipe-Grounded Conversationcited by 7
  11. 2023S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMscited by 7
  12. 2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
  13. 2022A Multi-Task BERT Model for Schema-Guided Dialogue State Trackingcited by 5
  14. 2022Knowledge-grounded Dialog State Trackingcited by 5
  15. 2023Continual Dialogue State Tracking via Example-Guided Question Answeringcited by 4
  16. 2023Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understandingcited by 4
  17. 2023Diable: Efficient Dialogue State Tracking as Operations on Tablescited by 4
  18. 2023Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schemacited by 3
  19. 2023Improving Generalization in Task-oriented Dialogues with Workflows and Action Planscited by 3
  20. 2024Chain of Thought Explanation for Dialogue State Trackingcited by 3
  21. 2023More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Rankingcited by 2
  22. 2023Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State Trackingcited by 2
  23. 2023Adapting Text-based Dialogue State Tracker for Spoken Dialoguescited by 2
  24. 2024Efficient Encoder-Decoder Transformer Decoding for Decomposable Taskscited by 2
  25. 2024A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understandingcited by 2
  26. 2024CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialoguescited by 2
  27. 2023Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turnscited by 1
  28. 2024Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Taskcited by 1
  29. 2024Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agentscited by 1
  30. 2024An Approach to Build Zero-Shot Slot-Filling System for Industry-Grade Conversational Assistantscited by 1
  31. 2024Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Trackingcited by 1
  32. 2024Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systemscited by 1
  33. 2025PyTOD: Programmable Task-Oriented Dialogue with Execution Feedbackcited by 1
  34. 2026ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Trackingcited by 1
  35. 2024Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Expertscited by 0
  36. 2024Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systemscited by 0
  37. 2025Beyond More Context: Retrieval Diversity Boosts Multi-Turn Intent Understandingcited by 0
  38. 2026Dynamic Knowledge Fusion for Multi-Domain Dialogue State Trackingcited by 0