Related papers: Reward-Driven Interaction: Enhancing Proactive Dia…
End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current…
Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors),…
User satisfaction is closely related to enterprises, as it not only directly reflects users' subjective evaluation of service quality or products, but also affects customer loyalty and long-term business revenue. Monitoring and…
Coping with ambiguous questions has been a perennial problem in real-world dialogue systems. Although clarification by asking questions is a common form of human interaction, it is hard to define appropriate questions to elicit more…
Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be…
This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's…
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and generation tasks while neglecting the exploitation of dialog…
Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention. Currently, many existing approaches formulate the DAR problem…
How might we design Reinforcement Learning (RL)-based recommenders that encourage aligning user trajectories with the underlying user satisfaction? Three research questions are key: (1) measuring user satisfaction, (2) combatting sparsity…
We will demonstrate a conversational products recommendation agent. This system shows how we combine research in personalized recommendation systems with research in dialogue systems to build a virtual sales agent. Based on new deep…
Agents that negotiate with humans find broad applications in pedagogy and conversational AI. Most efforts in human-agent negotiations rely on restrictive menu-driven interfaces for communication. To advance the research in language-based…
Like many other domains in Artificial Intelligence (AI), there are specific tasks in the field of AI in Education (AIEd) for which labels are scarce and expensive, such as predicting exam score or review correctness. A common way of…
Existing approaches to Dialogue State Tracking (DST) rely on turn level dialogue state annotations, which are expensive to acquire in large scale. In call centers, for tasks like managing bookings or subscriptions, the user goal can be…
Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…
Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with…
In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history. Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the…
Explainable AI techniques that describe agent reward functions can enhance human-robot collaboration in a variety of settings. One context where human understanding of agent reward functions is particularly beneficial is in the value…
Reinforcement learning methods are increasingly used to optimise dialogue policies from experience. Most current techniques are model-free: they directly estimate the utility of various actions, without explicit model of the interaction…
Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…
Existing simulations designed for cultural and interpersonal skill training rely on pre-defined responses with a menu option selection interface. Using a multiple-choice interface and restricting trainees' responses may limit the trainees'…