相关论文: How Pragmatics Shape Articulation: A Computational…

Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

Dialogue data has been a key source for understanding learning processes, offering critical insights into how students engage in collaborative discussions and how these interactions shape their knowledge construction. The advent of Large…

Speech language models (LMs) are promising for high-quality speech synthesis through in-context learning. A typical speech LM takes discrete semantic units as content and a short utterance as prompt, and synthesizes speech which preserves…

Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of these dialogues by treating them as regular text. In this…

Historically, sign language machine translation has been posed as a sentence-level task: datasets consisting of continuous narratives are chopped up and presented to the model as isolated clips. In this work, we explore the limitations of…

There have been recent advances in computer-based recognition of isolated, citation-form signs from video. There are many challenges for such a task, not least the naturally occurring inter- and intra- signer synchronic variation in sign…

Continual learning systems are increasingly deployed in environments where retraining or reset is infeasible, yet many approaches emphasize task performance rather than the evolution of internal representations over time. In this work, we…

Spoken Dialogue Models (SDMs) have recently attracted significant attention for their ability to generate voice responses directly to users' spoken queries. Despite their increasing popularity, there exists a gap in research focused on…

Although text-based large language models exhibit human-level writing ability and remarkable intelligence, speech language models (SLMs) still struggle to generate semantically coherent outputs. There are several potential reasons for this…

Continuous representations of logic formulae allow us to integrate symbolic knowledge into data-driven learning algorithms. If such embeddings are semantically consistent, i.e. if similar specifications are mapped into nearby vectors, they…

Emotions play a central role in human communication, shaping trust, engagement, and social interaction. As artificial intelligence systems powered by large language models become increasingly integrated into everyday life, enabling them to…

Human-computer dialog plays a prominent role in interactions conducted at kiosks (e.g., withdrawing money from an atm or filling your car with gas), on smartphones (e.g., installing and configuring apps), and on the web (e.g., booking a…

Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent…

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural…

Sign language recognition suffers from catastrophic scaling failure: models achieving high accuracy on small vocabularies collapse at realistic sizes. Existing architectures treat signs as atomic visual patterns, learning flat…

Like speech, signs are composed of discrete, recombinable features called phonemes. Prior work shows that models which can recognize phonemes are better at sign recognition, motivating deeper exploration into strategies for modeling sign…

Large Language models (LLMs) have shown remarkable success in assisting robot learning tasks, i.e., complex household planning. However, the performance of pretrained LLMs heavily relies on domain-specific templated text data, which may be…

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…