Related papers: Disentangling Syntax and Semantics in the Brain wi…
The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…
Large language models (LLMs) have revolutionized the field of natural language processing (NLP), and recent studies have aimed to understand their underlying mechanisms. However, most of this research is conducted within a monolingual…
Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…
This study investigates the ability of perceptron-type neurons in language models to perform intra-neuronal attention; that is, to identify different homogeneous categorical segments within the synthetic thought category they encode, based…
We present a mechanistic analysis of literary style in GPT-2, identifying individual neurons that discriminate between exemplary prose and rigid AI-generated text. Using Herman Melville's Bartleby, the Scrivener as a corpus, we extract…
Encouraged by the success of deep neural networks on a variety of visual tasks, much theoretical and experimental work has been aimed at understanding and interpreting how vision networks operate. Meanwhile, deep neural networks have also…
A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a…
We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…
Language decoding studies have identified word representations which can be used to predict brain activity in response to novel words and sentences (Anderson et al., 2016; Pereira et al., 2018). The unspoken assumption of these studies is…
Neuroimaging studies are often limited by the number of subjects and cognitive processes that can be feasibly interrogated. However, a rapidly growing number of neuroscientific studies have collectively accumulated an extensive wealth of…
Given the fast development of analysis techniques for NLP and speech processing systems, few systematic studies have been conducted to compare the strengths and weaknesses of each method. As a step in this direction we study the case of…
Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit…
We present novel methods for analyzing the activation patterns of RNNs from a linguistic point of view and explore the types of linguistic structure they learn. As a case study, we use a multi-task gated recurrent network architecture…
Diadochokinetic speech tasks (DDK), in which participants repeatedly produce syllables, are commonly used as part of the assessment of speech motor impairments. These studies rely on manual analyses that are time-intensive, subjective, and…
The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…
Neuroscientists evaluate deep neural networks for natural language processing as possible candidate models for how language is processed in the brain. These models are often trained without explicit linguistic supervision, but have been…
We analyze the complex networks associated with brain electrical activity. Multichannel EEG measurements are first processed to obtain 3D voxel activations using the tomographic algorithm LORETA. Then, the correlation of the current…
Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better…
Understanding how neural activity encodes speech and language production is a fundamental challenge in neuroscience and artificial intelligence. This study investigates whether embeddings from large-scale, self-supervised language and…