mlsanityData to 7 Oct 2026

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

arXiv 2106.00291 ↗First posted 1 Jun 2021cs.CLcited by 35

Not on the map. Why?

Abstract (arXiv)

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset. In this paper, we propose to use curriculum learning (CL) to better leverage both the curriculum structure and schema structure for task-oriented dialogs. Specifically, we propose a model-agnostic framework called Schema-aware Curriculum Learning for Dialog State Tracking (SaCLog), which consists of a preview module that pre-trains a DST model with schema information, a curriculum module that optimizes the model with CL, and a review module that augments mispredicted data to reinforce the CL training. We show that our proposed approach improves DST performance over both a transformer-based and RNN-based DST model (TripPy and TRADE) and achieves new state-of-the-art results on WOZ2.0 and MultiWOZ2.1.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 28 of its 40 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

28 of 40 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018Deep contextualized word representationscited by 2,285
  4. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  5. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  6. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  7. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  8. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  9. 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
  10. 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
  11. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  12. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
16 more
  1. 2018Sequence-to-Sequence Data Augmentation for Dialogue Language Understandingcited by 67
  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. 2020Norm-Based Curriculum Learning for Neural Machine Translationcited by 60
  6. 2019Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narrativescited by 59
  7. 2018Global-Locally Self-Attentive Dialogue State Trackercited by 45
  8. 2020CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackerscited by 43
  9. 2020Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Trackingcited by 27
  10. 2020Dialogue Response Selection with Hierarchical Curriculum Learningcited by 27
  11. 2020A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Trackingcited by 20
  12. 2019Dialog State Tracking with Reinforced Data Augmentationcited by 10
  13. 2020Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentationcited by 9
  14. 2020Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learningcited by 8
  15. 2020Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generationcited by 6
  16. 2017Tracking of enriched dialog states for flexible conversational information accesscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 19; 2023: 10; 2024: 4; 2025: 1.

35 papers.

Sort:

By area:

  1. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  2. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  3. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  4. 2024A Full-duplex Speech Dialogue Scheme Based On Large Language Modelscited by 40
  5. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  6. 2023A Preliminary Study of the Intrinsic Relationship between Complexity and Alignmentcited by 33
  7. 2022Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsingcited by 30
  8. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  9. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  10. 2022Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systemscited by 28
  11. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  12. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
23 more
  1. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
  2. 2022Robust Dialogue State Tracking with Weak Supervision and Sparse Datacited by 15
  3. 2022A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slotscited by 13
  4. 2022NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialoguecited by 8
  5. 2022Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialoguecited by 8
  6. 2023Empathetic Response Generation via Emotion Cause Transition Graphcited by 8
  7. 2022LUNA: Learning Slot-Turn Alignment for Dialogue State Trackingcited by 6
  8. 2022Multimodal Dialogue State Trackingcited by 6
  9. 2023PromptAttack: Probing Dialogue State Trackers with Adversarial Promptscited by 6
  10. 2022OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialoguecited by 4
  11. 2022Confidence-Guided Learning Process for Continuous Classification of Time Seriescited by 3
  12. 2022MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Trackingcited by 3
  13. 2023A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systemscited by 3
  14. 2022A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Rankingcited by 2
  15. 2025Multi-Intent Recognition in Dialogue Understanding: A Comparison Between Smaller Open-Source LLMscited by 2
  16. 2022Multi-Domain Targeted Sentiment Analysiscited by 1
  17. 2023Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Trackingcited by 1
  18. 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systemscited by 1
  19. 2024Can Similarity-Based Domain-Ordering Reduce Catastrophic Forgetting for Intent Recognition?cited by 1
  20. 2022Schema Encoding for Transferable Dialogue State Trackingcited by 0
  21. 2023Curricular Transfer Learning for Sentence Encoded Taskscited by 0
  22. 2023Turn-Level Active Learning for Dialogue State Trackingcited by 0
  23. 2024Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Expertscited by 0