Related papers: Pseudo-Label Enhanced Prototypical Contrastive Lea…
New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and service expansion of a practical dialogue system. Despite its…
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined…
Generalized intent discovery aims to extend a closed-set in-domain intent classifier to an open-world intent set including in-domain and out-of-domain intents. The key challenges lie in pseudo label disambiguation and representation…
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the…
Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals…
Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain…
Discovering out-of-domain (OOD) intent is important for developing new skills in task-oriented dialogue systems. The key challenges lie in how to transfer prior in-domain (IND) knowledge to OOD clustering, as well as jointly learn OOD…
Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most…
Although existing semi-supervised learning models achieve remarkable success in learning with unannotated in-distribution data, they mostly fail to learn on unlabeled data sampled from novel semantic classes due to their closed-set…
Pretext Invariant Representation Learning (PIRL) followed by Supervised Fine-Tuning (SFT) has become a standard paradigm for learning with limited labels. We extend this approach to the Positive Unlabeled (PU) setting, where only a small…
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on…
Deriving value from a conversational AI system depends on the capacity of a user to translate the prior knowledge into a configuration. In most cases, discovering the set of relevant turn-level speaker intents is often one of the key steps.…
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a…
Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of…
Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by…
Open intent classification, which aims to correctly classify the known intents into their corresponding classes while identifying the new unknown (open) intents, is an essential but challenging task in dialogue systems. In this paper, we…
Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin…
Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world…
Capturing emotions within a conversation plays an essential role in modern dialogue systems. However, the weak correlation between emotions and semantics brings many challenges to emotion recognition in conversation (ERC). Even semantically…
Intent Detection is one of the tasks of the Natural Language Understanding (NLU) unit in task-oriented dialogue systems. Out of Scope (OOS) and Out of Domain (OOD) inputs may run these systems into a problem. On the other side, a labeled…