mlsanityData to 7 Oct 2026

N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking

arXiv 2103.00293 ↗First posted 27 Feb 2021cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 27 Feb 2021.

Builds on

28 of 42 references.

References · 28

  1. 2016Wide Residual Networkscited by 3,057
  2. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  3. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  4. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  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. 2018Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relationscited by 201
  8. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  9. 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
  10. 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
  11. 2017Data Noising as Smoothing in Neural Network Language Modelscited by 78
  12. 2018Sequence-to-Sequence Data Augmentation for Dialogue Language Understandingcited by 67
16 more
  1. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  2. 2018Global-Locally Self-Attentive Dialogue State Trackercited by 45
  3. 2020Paraphrase Augmented Task-Oriented Dialog Generationcited by 43
  4. 2020CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackerscited by 43
  5. 2020Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representationscited by 42
  6. 2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
  7. 2020Coach: A Coarse-to-Fine Approach for Cross-domain Slot Fillingcited by 38
  8. 2018Large-Scale Multi-Domain Belief Tracking with Knowledge Sharingcited by 29
  9. 2017Scalable Multi-Domain Dialogue State Trackingcited by 22
  10. 2021Few Shot Dialogue State Tracking using Meta-learningcited by 16
  11. 2020Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Managementcited by 13
  12. 2019Dialog State Tracking with Reinforced Data Augmentationcited by 10
  13. 2019Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialoguecited by 7
  14. 2020Data Augmentation for Copy-Mechanism in Dialogue State Trackingcited by 7
  15. 2019Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoringcited by 5
  16. 2018Automatic Data Expansion for Customer-care Spoken Language Understandingcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 1.

6 papers.

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  3. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  4. 2024Dual-path Frequency Discriminators for Few-shot Anomaly Detectioncited by 7
  5. 2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
  6. 2025Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactionscited by 2