mlsanityData to 7 Oct 2026

Global-Locally Self-Attentive Dialogue State Tracker

arXiv 1805.09655 ↗First posted 19 May 2018cs.CL cs.AIcited by 45

Not on the map. Why?

Abstract (arXiv)

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achieves state-of-the-art performance on the WoZ and DSTC2 state tracking tasks. GLAD obtains 88.1% joint goal accuracy and 97.1% request accuracy on WoZ, outperforming prior work by 3.7% and 5.5%. On DSTC2, our model obtains 74.5% joint goal accuracy and 97.5% request accuracy, outperforming prior work by 1.1% and 1.0%.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 17; 2022: 11; 2023: 6; 2024: 6; 2025: 3; 2026: 1.

45 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. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  5. 2021Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Trackingcited by 35
  6. 2021Slot Self-Attentive Dialogue State Trackingcited by 27
  7. 2021Amendable Generation for Dialogue State Trackingcited by 21
  8. 2022Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Trackingcited by 18
  9. 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
  10. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  11. 2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
  12. 2022Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulatorcited by 15
33 more
  1. 2022KETOD: Knowledge-Enriched Task-Oriented Dialoguecited by 11
  2. 2021Contextual Semantic Parsing for Multilingual Task-Oriented Dialoguescited by 10
  3. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  4. 2021Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memorycited by 8
  5. 2021Text is no more Enough! A Benchmark for Profile-based Spoken Language Understandingcited by 7
  6. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  7. 2024Learning to Ask: Conversational Product Search via Representation Learningcited by 7
  8. 2021N-Shot Learning for Augmenting Task-Oriented Dialogue State Trackingcited by 6
  9. 2022LUNA: Learning Slot-Turn Alignment for Dialogue State Trackingcited by 6
  10. 2022Multimodal Dialogue State Trackingcited by 6
  11. 2021Dual Slot Selector via Local Reliability Verification for Dialogue State Trackingcited by 5
  12. 2024Are Human Conversations Special? A Large Language Model Perspectivecited by 5
  13. 2019A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Expertscited by 4
  14. 2021SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domaincited by 4
  15. 2022Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Trackingcited by 4
  16. 2022OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialoguecited by 4
  17. 2023Diable: Efficient Dialogue State Tracking as Operations on Tablescited by 4
  18. 2021Task-oriented Dialogue Systems: performance vs. quality-optima, a reviewcited by 3
  19. 2024Chain of Thought Explanation for Dialogue State Trackingcited by 3
  20. 2022XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Trackingcited by 2
  21. 2024Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language Understandingcited by 2
  22. 2022A Chit-Chats Enhanced Task-Oriented Dialogue Corpora for Fuse-Motive Conversation Systemscited by 1
  23. 2023Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Trackingcited by 1
  24. 2023Is one brick enough to break the wall of spoken dialogue state tracking?cited by 1
  25. 2024A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generationcited by 1
  26. 2025Conversational Assistants to support Heart Failure Patients: comparing a Neurosymbolic Architecture with ChatGPTcited by 1
  27. 2025The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approachcited by 1
  28. 2021Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Trackingcited by 0
  29. 2021Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Trackingcited by 0
  30. 2021Ontology-Enhanced Slot Fillingcited by 0
  31. 2022Schema Encoding for Transferable Dialogue State Trackingcited by 0
  32. 2025Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modelingcited by 0
  33. 2026Candidate Attended Dialogue State Tracking Using BERTcited by 0