mlsanityData to 7 Oct 2026

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

arXiv 1907.07421 ↗First posted 17 Jul 2019cs.CL cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

In goal-oriented dialog systems, belief trackers estimate the probability distribution of slot-values at every dialog turn. Previous neural approaches have modeled domain- and slot-dependent belief trackers, and have difficulty in adding new slot-values, resulting in lack of flexibility of domain ontology configurations. In this paper, we propose a new approach to universal and scalable belief tracker, called slot-utterance matching belief tracker (SUMBT). The model learns the relations between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors. Furthermore, the model predicts slot-value labels in a non-parametric way. From our experiments on two dialog corpora, WOZ 2.0 and MultiWOZ, the proposed model showed performance improvement in comparison with slot-dependent methods and achieved the state-of-the-art joint accuracy.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 20; 2023: 10; 2024: 5; 2025: 2; 2026: 3.

63 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  3. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  4. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  5. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  6. 2022Continual Prompt Tuning for Dialog State Trackingcited by 44
  7. 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
  8. 2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
  9. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  10. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  11. 2021Slot Self-Attentive Dialogue State Trackingcited by 27
  12. 2023Towards LLM-driven Dialogue State Trackingcited by 25
38 more
  1. 2021Gradual Fine-Tuning for Low-Resource Domain Adaptationcited by 23
  2. 2023A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Modelscited by 23
  3. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  4. 2021Effective Sequence-to-Sequence Dialogue State Trackingcited by 20
  5. 2022BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialogcited by 20
  6. 2021Few Shot Dialogue State Tracking using Meta-learningcited by 16
  7. 2021NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulationcited by 16
  8. 2022Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialoguecited by 16
  9. 2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
  10. 2022Extrinsic Evaluation of Machine Translation Metricscited by 14
  11. 2021Cross-lingual Intermediate Fine-tuning improves Dialogue State Trackingcited by 11
  12. 2022ASSIST: Towards Label Noise-Robust Dialogue State Trackingcited by 11
  13. 2022Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialogcited by 11
  14. 2021Contextual Semantic Parsing for Multilingual Task-Oriented Dialoguescited by 10
  15. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  16. 2021Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performancecited by 8
  17. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  18. 2022LUNA: Learning Slot-Turn Alignment for Dialogue State Trackingcited by 6
  19. 2022Multimodal Dialogue State Trackingcited by 6
  20. 2021Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?cited by 5
  21. 2021Dual Slot Selector via Local Reliability Verification for Dialogue State Trackingcited by 5
  22. 2022On Tracking Dialogue State by Inheriting Slot Values in Mentioned Slot Poolscited by 5
  23. 2022Instilling Type Knowledge in Language Models via Multi-Task QAcited by 5
  24. 2026Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streamscited by 5
  25. 2022Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Trackingcited by 4
  26. 2022OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialoguecited by 4
  27. 2023DialogVCS: Robust Natural Language Understanding in Dialogue System Upgradecited by 4
  28. 2023Diable: Efficient Dialogue State Tracking as Operations on Tablescited by 4
  29. 2022MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Trackingcited by 3
  30. 2024Multi-Modal Video Dialog State Tracking in the Wildcited by 3
  31. 2021Oh My Mistake!: Toward Realistic Dialogue State Tracking including Turnback Utterancescited by 2
  32. 2022XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Trackingcited by 2
  33. 2026Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignmentcited by 2
  34. 2021Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog Systemcited by 1
  35. 2023Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Trackingcited by 1
  36. 2023Choice Fusion as Knowledge for Zero-Shot Dialogue State Trackingcited by 1
  37. 2024MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Trackingcited by 1
  38. 2021Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Trackingcited by 0

50 most cited of 63 All 63 (JSON)