mlsanityData to 7 Oct 2026

Few Shot Dialogue State Tracking using Meta-learning

arXiv 2101.06779 ↗First posted 17 Jan 2021cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models, and datasets with significant (5-25%) improvement over the baseline in a low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 24 of its 27 references that are in the map. First posted on arXiv 17 Jan 2021.

Builds on

24 of 27 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  6. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 851
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  9. 2020On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselinescited by 254
  10. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  11. 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 183
  12. 2019DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehensioncited by 156
12 more
  1. 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
  2. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  3. 2019Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Trackingcited by 75
  4. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  5. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  6. 2019Revisiting Low-Resource Neural Machine Translation: A Case Studycited by 61
  7. 2019Learning to Few-Shot Learn Across Diverse Natural Language Classification Taskscited by 57
  8. 2019Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Taskscited by 48
  9. 2019Domain Adaptive Dialog Generation via Meta Learningcited by 41
  10. 2020From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gapcited by 40
  11. 2018Natural Language to Structured Query Generation via Meta-Learningcited by 33
  12. 2019HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Trackingcited by 14

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 3; 2024: 6.

16 papers.

Sort:

By area:

  1. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  2. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  3. 2023In-Context Learning User Simulators for Task-Oriented Dialog Systemscited by 19
  4. 2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingcited by 17
  5. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  6. 2021Generative Conversational Networkscited by 11
  7. 2022A Dual Prompt Learning Framework for Few-Shot Dialogue State Trackingcited by 8
  8. 2023Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuningcited by 8
  9. 2021N-Shot Learning for Augmenting Task-Oriented Dialogue State Trackingcited by 6
  10. 2023Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Trackingcited by 6
  11. 2024Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentationcited by 2
  12. 2024Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Trackingcited by 1
4 more
  1. 2022A Study on Prompt-based Few-Shot Learning Methods for Belief State Tracking in Task-oriented Dialog Systemscited by 0
  2. 2022Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Trackingcited by 0
  3. 2024State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Trackingcited by 0
  4. 2024Training Zero-Shot Generalizable End-to-End Task-Oriented Dialog System Without Turn-level Dialog Annotationscited by 0