CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking

• URL: http://arxiv.org/abs/2210.05146v1
• Date: Tue, 11 Oct 2022 04:55:16 GMT
• Title: CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking
• Authors: Haoning Zhang, Junwei Bao, Haipeng Sun, Huaishao Luo, Wenye Li, Shuguang Cui
• Abstract summary: Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. We propose a few-shot DST framework called CSS, which Combines Self-training and Self-supervised learning methods. Experimental results on the MultiWOZ dataset show that our proposed CSS achieves competitive performance in several few-shot scenarios.
• Score: 36.18207750352937
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., from question answering, dialogue summarization, machine reading comprehension tasks, etc.) into DST, whereas collecting a large amount of external labeled data is laborious, and the external data may not effectively contribute to the DST-specific task. In this paper, we propose a few-shot DST framework called CSS, which Combines Self-training and Self-supervised learning methods. The unlabeled data of the DST task is incorporated into the self-training iterations, where the pseudo labels are predicted by a DST model trained on limited labeled data in advance. Besides, a contrastive self-supervised method is used to learn better representations, where the data is augmented by the dropout operation to train the model. Experimental results on the MultiWOZ dataset show that our proposed CSS achieves competitive performance in several few-shot scenarios.

Related papers

• Incremental Self-training for Semi-supervised Learning [56.57057576885672]
  IST is simple yet effective and fits existing self-training-based semi-supervised learning methods. We verify the proposed IST on five datasets and two types of backbone, effectively improving the recognition accuracy and learning speed.
  arXiv  Detail & Related papers  (2024-04-14T05:02:00Z)
• UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking [54.51316566989655]
  Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain. We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training methods. We demonstrate this method's effectiveness on general language models in zero-shot scenarios, improving average joint goal accuracy by 8% across all domains in MultiWOZ.
  arXiv  Detail & Related papers  (2023-10-16T15:16:16Z)
• PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts [25.467840115593784]
  A key component of modern conversational systems is the Dialogue State Tracker (or DST) We introduce a prompt-based learning approach to automatically generate effective adversarial examples to probe DST models. We show how much the generated adversarial examples can bolster a DST through adversarial training.
  arXiv  Detail & Related papers  (2023-06-07T15:41:40Z)
• Prompt Learning for Few-Shot Dialogue State Tracking [75.50701890035154]
  This paper focuses on how to learn a dialogue state tracking (DST) model efficiently with limited labeled data. We design a prompt learning framework for few-shot DST, which consists of two main components: value-based prompt and inverse prompt mechanism. Experiments show that our model can generate unseen slots and outperforms existing state-of-the-art few-shot methods.
  arXiv  Detail & Related papers  (2022-01-15T07:37:33Z)
• Improving Limited Labeled Dialogue State Tracking with Self-Supervision [91.68515201803986]
  Existing dialogue state tracking (DST) models require plenty of labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. Our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used.
  arXiv  Detail & Related papers  (2020-10-26T21:57:42Z)
• Dual Learning for Dialogue State Tracking [44.679185483585364]
  Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding. We propose a novel dual-learning framework to make full use of unlabeled data.
  arXiv  Detail & Related papers  (2020-09-22T10:15:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.