Related papers: From "um" to "yeah": Producing, predicting, and re…
Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept. Such a tendency can be seen in generative tasks like question-answering and dialogue…
The analysis of thousands of time series in different languages reveals that word usage presents oscillations with a prevalence of 16-year cycles, mounted on slowly varying trends. These components carry different information: while similar…
Existing conversational datasets consist either of written proxies for dialog or small-scale transcriptions of natural speech. We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview…
Dialogue is at the core of human behaviour and being able to identify the topic at hand is crucial to take part in conversation. Yet, there are few accounts of the topical organisation in casual dialogue and of how people recognise the…
Forecasting conversation derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite language models' success at identifying offensive speech present in…
In spoken communication, information is transmitted not only via words, but also through a rich array of non-verbal signals, including prosody--the non-segmental auditory features of speech. Do these different communication channels carry…
Many neural network models nowadays have achieved promising performances in Chit-chat settings. The majority of them rely on an encoder for understanding the post and a decoder for generating the response. Without given assigned semantics,…
The uniform information density (UID) hypothesis posits a preference among language users for utterances structured such that information is distributed uniformly across a signal. While its implications on language production have been well…
The way that humans encode their emotion into speech signals is complex. For instance, an angry man may increase his pitch and speaking rate, and use impolite words. In this paper, we present a preliminary study on various emotional factors…
The applications of large language models (LLMs) have been widely spread across all domains. However, the basic abilities such as the controllability of LLMs are still limited. To address this, we propose "Self-controller", a novel agentic…
We consider the problem of transmitting classical information over a time-invariant channel with memory. A popular class of time-invariant channels with memory are finite-state-machine channels, where a \emph{classical} state evolves over…
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficiently compress meanings into communication signals by…
Living entities in a group communicate and transfer information to one another for a variety of reasons. It might be for foraging food, migration, or escaping threats and obstacles, etc. They do so by interacting with each other and also…
Language models will inevitably err in situations with which they are unfamiliar. However, by effectively communicating uncertainties, they can still guide humans toward making sound decisions in those contexts. We demonstrate this idea by…
Visual information is central to conversation: body gestures and physical behaviour, for example, contribute to meaning that transcends words alone. To date, however, most neural conversational models are limited to just text. We introduce…
The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two…
Speech is a distinctive complex feature of human capabilities. In order to understand the physics underlying speech production, in this work we empirically analyse the statistics of large human speech datasets ranging several languages. We…
Despite end-to-end neural systems making significant progress in the last decade for task-oriented as well as chit-chat based dialogue systems, most dialogue systems rely on hybrid approaches which use a combination of rule-based, retrieval…
Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…
Information theory is a practical and theoretical framework developed for the study of communication over noisy channels. Its probabilistic basis and capacity to relate statistical structure to function make it ideally suited for studying…