相关论文: Associative Syntax and Maximal Repetitions reveal …

Symbolic perturbations offer a novel approach for influencing neural representations without requiring direct modification of model parameters. The recursive regeneration of symbolic structures introduces structured variations in latent…

Pre-trained language models perform well on a variety of linguistic tasks that require symbolic reasoning, raising the question of whether such models implicitly represent abstract symbols and rules. We investigate this question using the…

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…

Understanding a discourse requires tracking entities and the relations that hold between them. While Large Language Models (LLMs) perform well on relational reasoning, the mechanism by which they bind entities, relations, and attributes…

Accurate transcription and speaker diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems…

Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are commonly used for such speaker adaptation, they require computationally expensive retraining for…

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and…

Experiments probing natural language processing by both humans and LLMs suggest that the meaning of a semantic expression is indeterminate prior to the act of interpretation rather than being specifiable simply as the sum of its parts (i.e.…

Small and mid-sized generative language models have gained increasing attention. Their size and availability make them amenable to being analyzed at a behavioral as well as a representational level, allowing investigations of how these…

Recent work has demonstrated that neural language models encode syntactic structures in their internal representations, yet the derivations by which these structures are constructed across layers remain poorly understood. In this paper, we…

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

In recent years, we have seen a colossal effort in pre-training multilingual text encoders using large-scale corpora in many languages to facilitate cross-lingual transfer learning. However, due to typological differences across languages,…

Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct…

In music and speech, meaning is derived at multiple levels of context. Affect, for example, can be inferred both by a short sound token and by sonic patterns over a longer temporal window such as an entire recording. In this letter, we…

Large Language Models (LLMs) have become integral to software engineering workflows, yet their effectiveness degrades significantly in multi-turn conversations. Recent studies demonstrate an average 39% performance drop when instructions…

We present a sequential model for temporal relation classification between intra-sentence events. The key observation is that the overall syntactic structure and compositional meanings of the multi-word context between events are important…

This paper proposes a new approach to Machine Learning (ML) that focuses on unsupervised continuous context-dependent learning of complex patterns. Although the proposal is partly inspired by some of the current knowledge about the…

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in…

This work studies distributed learning in the spirit of Yao's model of communication complexity: consider a two-party setting, where each of the players gets a list of labelled examples and they communicate in order to jointly perform some…