mlsanityData to 14 Oct 2026

Improving Limited Labeled Dialogue State Tracking with Self-Supervision

arXiv 2010.13920 ↗First posted 26 Oct 2020cs.CL cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is rarely discussed, i.e., learning efficiently with limited labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. We encourage a DST model to have consistent latent distributions given a perturbed input, making it more robust to an unseen scenario. We also add an auxiliary utterance generation task, modeling a potential correlation between conversational behavior and dialogue states. The experimental results show that our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used on the MultiWOZ dataset. We can achieve an additional 1.76% improvement if some unlabeled data is jointly trained as semi-supervised learning. We analyze and visualize how our proposed self-supervised signals help the DST task and hope to stimulate future data-efficient DST research.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 4; 2024: 5.

16 papers.

Sort:

By area:

  1. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  2. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  3. 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
  4. 2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
  5. 2023Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuningcited by 21
  6. 2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 19
  7. 2023Diverse Retrieval-Augmented In-Context Learning for Dialogue State Trackingcited by 10
  8. 2022DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuningcited by 9
  9. 2022A Dual Prompt Learning Framework for Few-Shot Dialogue State Trackingcited by 8
  10. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
  11. 2024Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logiccited by 5
  12. 2021Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervisioncited by 3
4 more
  1. 2022CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Trackingcited by 1
  2. 2023UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Trackingcited by 1
  3. 2024CorrectionLM: Self-Corrections with SLM for Dialogue State Trackingcited by 1
  4. 2024State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Trackingcited by 0