Related papers: A Hybrid Solution to Learn Turn-Taking in Multi-Pa…
Studies in human human interaction have introduced the concept of F formation to describe the spatial arrangement of participants during social interactions. This paper has two objectives. It aims at detecting F formations in video…
Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatbots that determine "What" to answer. This paper highlights…
Previous attempts to build effective semantic parsers for Wizard-of-Oz (WOZ) conversations suffer from the difficulty in acquiring a high-quality, manually annotated training set. Approaches based only on dialogue synthesis are…
Learned communication makes multi-agent systems more effective by aggregating distributed information. However, it also exposes individual agents to the threat of erroneous messages they might receive. In this paper, we study the setting…
Multi-turn conversations are a common and critical mode of language model interaction. However, current open training and evaluation data focus on single-turn settings, failing to capture the additional dimension of these longer…
Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pairs. Although the context contains the complete dialogue…
In this letter we propose a data-driven approach to optimizing the algebraic connectivity of a team of robots. While a considerable amount of research has been devoted to this problem, we lack a method that scales in a manner suitable for…
Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available. To address this fundamental obstacle, we introduce the Multi-Domain Wizard-of-Oz…
Turn-taking is essential to the structure of human teamwork. Humans are typically aware of team members' intention to keep or relinquish their turn before a turn switch, where the responsibility of working on a shared task is shifted.…
Task-oriented dialogue systems have garnered significant attention due to their conversational ability to accomplish goals, such as booking airline tickets for users. Traditionally, task-oriented dialogue systems are conceptualized as…
Lane change (LC) is one of the safety-critical manoeuvres in highway driving according to various road accident records. Thus, reliably predicting such manoeuvre in advance is critical for the safe and comfortable operation of automated…
Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of…
We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…
Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation…
Dialogue models are inherently reactive, responding to the current user turn without anticipating upcoming intents, which leads to redundant interactions in multi-intent settings. We address this limitation by introducing a lightweight…
We propose NeuralWOZ, a novel dialogue collection framework that uses model-based dialogue simulation. NeuralWOZ has two pipelined models, Collector and Labeler. Collector generates dialogues from (1) user's goal instructions, which are the…
Most current speech technology systems are designed to operate well even in the presence of multiple active speakers. However, most solutions assume that the number of co-current speakers is known. Unfortunately, this information might not…
Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging…
This paper explores how large language models can leverage multi-level contextual information to predict group coordination patterns in collaborative mixed reality environments. We demonstrate that encoding individual behavioral profiles,…