Recently, large pretrained language models have demonstrated strong language
understanding capabilities. This is particularly reflected in their zero-shot and in-context …

Multi-intent detection and slot filling joint models are gaining increasing traction since they
are closer to complicated real-world scenarios. However, existing approaches (1) focus on …

Large Language Models (LLMs) have sparked substantial interest and debate concerning
their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations …

In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for
enhancing the adaptability and robustness of conversational agents. Traditional models rely …

Abstract Zero-shot Spoken Language Understanding (SLU) aims to enable task-oriented
dialogue systems to understand user needs without training data. Challenging but …

This paper focuses on multi-intent detection in the few-shot scenario. Most prior works for
multi-intent detection pick intent labels when estimated label-instance relevance scores are …

Human–robot interaction is becoming increasingly common to perform useful tasks in
everyday life. From the human–machine communication perspective, achieving effective …

Few-shot intent detection is a challenging task, particularly in scenarios involving multiple
labels and diverse domains. This paper presents a novel prototype learning approach that …

Intent detection and slot filling are two main tasks in natural language understanding and
play an essential role in task-oriented dialogue systems. The joint learning of both tasks can …

Interaction is a dynamic process that evolves in real time. Participants interpret and orient
themselves towards turns of speech based on expectations of relevance and …