Related papers: Self-Training with Purpose Preserving Augmentation…

In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be…

Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords. However, existing KWS datasets are limited in scale and gathering keyword-like labeled data is costly…

Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model…

Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent…

In a task-oriented dialog system, the goal of dialog state tracking (DST) is to monitor the state of the conversation from the dialog history. Recently, many deep learning based methods have been proposed for the task. Despite their…

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have…

Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is…

Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each…

Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…

Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined…

Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen…

Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL,…

Dialogue state tracking (DST) is a key component of task-oriented dialogue systems. DST estimates the user's goal at each user turn given the interaction until then. State of the art approaches for state tracking rely on deep learning…

Dialogue state tracking (DST) is a component of the task-oriented dialogue system. It is responsible for extracting and managing slot values according to dialogue utterances, where each slot represents an essential part of the information…

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to…

Tutoring is an effective instructional method for enhancing student learning, yet its success relies on the skill and experience of the tutors. This reliance presents challenges for the widespread implementation of tutoring, particularly in…

Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of pre-trained language models when labeled data is insufficient. However, it remains challenging to incorporate ST into attribute-controllable…

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…

Training the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems. Existing methods tend to use the meta-learning framework which pre-trains the parameters on all non-target tasks…