mlsanityData to 7 Oct 2026

Zero-shot Generalization in Dialog State Tracking through Generative Question Answering

arXiv 2101.08333 ↗First posted 20 Jan 2021cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs. In real-world settings with constantly changing services, DST systems must generalize to new domains and unseen slot types. Existing methods for DST do not generalize well to new slot names and many require known ontologies of slot types and values for inference. We introduce a novel ontology-free framework that supports natural language queries for unseen constraints and slots in multi-domain task-oriented dialogs. Our approach is based on generative question-answering using a conditional language model pre-trained on substantive English sentences. Our model improves joint goal accuracy in zero-shot domain adaptation settings by up to 9% (absolute) over the previous state-of-the-art on the MultiWOZ 2.1 dataset.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 40 of its 51 references that are in the map. First posted on arXiv 20 Jan 2021.

Builds on

40 of 51 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  8. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  9. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  10. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  11. 2019Language Models as Knowledge Bases?cited by 1,922
  12. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
28 more
  1. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  2. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
  3. 2019ELI5: Long Form Question Answeringcited by 567
  4. 2014Deep metric learning using Triplet networkcited by 421
  5. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  6. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
  7. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  8. 2017Learning to Ask: Neural Question Generation for Reading Comprehensioncited by 186
  9. 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 183
  10. 2019Do NLP Models Know Numbers? Probing Numeracy in Embeddingscited by 157
  11. 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 142
  12. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  13. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  14. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  15. 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
  16. 2018Building a Conversational Agent Overnight with Dialogue Self-Playcited by 70
  17. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  18. 2020End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systemscited by 65
  19. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  20. 2019Dialog State Tracking: A Neural Reading Comprehension Approachcited by 62
  21. 2018Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numberscited by 42
  22. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  23. 2019Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answeringcited by 39
  24. 2018Large-Scale Multi-Domain Belief Tracking with Knowledge Sharingcited by 29
  25. 2018An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Trackingcited by 27
  26. 2019The Eighth Dialog System Technology Challengecited by 25
  27. 2020MA-DST: Multi-Attention Based Scalable Dialog State Trackingcited by 24
  28. 2019Unifying Question Answering, Text Classification, and Regression via Span Extractioncited by 8

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 12; 2023: 9; 2024: 6; 2025: 2.

33 papers.

Sort:

By area:

  1. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  2. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  3. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  4. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
  5. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  6. 2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
  7. 2021QAConv: Question Answering on Informative Conversationscited by 17
  8. 2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 17
  9. 2021NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulationcited by 16
  10. 2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
  11. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  12. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
21 more
  1. 2021Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generationcited by 8
  2. 2022A Dual Prompt Learning Framework for Few-Shot Dialogue State Trackingcited by 8
  3. 2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
  4. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
  5. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  6. 2022Instilling Type Knowledge in Language Models via Multi-Task QAcited by 5
  7. 2023Continual Dialogue State Tracking via Example-Guided Question Answeringcited by 4
  8. 2023Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schemacited by 3
  9. 2024Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPTcited by 3
  10. 2022XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Trackingcited by 2
  11. 2022Controllable User Dialogue Act Augmentation for Dialogue State Trackingcited by 2
  12. 2022SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Taskcited by 2
  13. 2024A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understandingcited by 2
  14. 2025Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Modelscited by 2
  15. 2023Choice Fusion as Knowledge for Zero-Shot Dialogue State Trackingcited by 1
  16. 2023UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Trackingcited by 1
  17. 2024Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agentscited by 1
  18. 2024CorrectionLM: Self-Corrections with SLM for Dialogue State Trackingcited by 1
  19. 2024Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Trackingcited by 1
  20. 2022Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialogcited by 0
  21. 2025HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DSTcited by 0