Related papers: Evaluating Prerequisite Qualities for Learning End…
End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…
Encoder-decoder based neural architectures serve as the basis of state-of-the-art approaches in end-to-end open domain dialog systems. Since most of such systems are trained with a maximum likelihood~(MLE) objective they suffer from issues…
Embodied agents designed to assist users with tasks must engage in natural language interactions, interpret instructions, execute actions, and communicate effectively to resolve issues. However, collecting large-scale, diverse datasets of…
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. A part of this effort is the policy optimisation task, which attempts to find a policy describing how to…
Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors. Although there have been significant recent advances in neural conversational systems using large…
Automatic evaluation is an integral aspect of dialogue system research. The traditional reference-based NLG metrics are generally found to be unsuitable for dialogue assessment. Consequently, recent studies have suggested various unique,…
A good dialogue agent should have the ability to interact with users by both responding to questions and by asking questions, and importantly to learn from both types of interaction. In this work, we explore this direction by designing a…
Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks.…
This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current…
This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems. Recent end-to-end generation systems are promising since they reduce the…
Dialogue systems have attracted more and more attention. Recent advances on dialogue systems are overwhelmingly contributed by deep learning techniques, which have been employed to enhance a wide range of big data applications such as…
Open-domain dialogue systems have started to engage in continuous conversations with humans. Those dialogue systems are required to be adjusted to the human interlocutor and evaluated in terms of their perspective. However, it is…
End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of…
Autonomy is fundamental for artificial agents acting in complex real-world scenarios. The acquisition of many different skills is pivotal to foster versatile autonomous behaviour and thus a main objective for robotics and machine learning.…
Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have become more complex, making them harder to understand. To this end, researchers have proposed several techniques to…
End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few…
Task-oriented dialog systems have been applied in various tasks, such as automated personal assistants, customer service providers and tutors. These systems work well when users have clear and explicit intentions that are well-aligned to…
Pre-trained conversation models (PCMs) have achieved promising progress in recent years. However, existing PCMs for Task-oriented dialog (TOD) are insufficient for capturing the sequential nature of the TOD-related tasks, as well as for…
Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth reasoning beyond pattern-based scoring. Recent efforts start to leverage large language models (LLMs)…
Existing goal-oriented dialogue datasets focus mainly on identifying slots and values. However, customer support interactions in reality often involve agents following multi-step procedures derived from explicitly-defined company policies…