The activations of language transformers like GPT-2 have been shown to linearly map onto brain activity during speech comprehension. However, the nature of these activations remains largely unknown and presumably conflate distinct linguistic classes. Here, we propose a taxonomy to factorize the high-dimensional activations of language models into four combinatorial classes: lexical, compositional, syntactic, and semantic representations. We then introduce a statistical method to decompose, through the lens of GPT-2's activations, the brain activity of 345 subjects recorded with functional magnetic resonance imaging (fMRI) during the listening of ~4.6 hours of narrated text. The results highlight two findings. First, compositional representations recruit a more widespread cortical network than lexical ones, and encompass the bilateral temporal, parietal and prefrontal cortices. Second, contrary to previous claims, syntax and semantics are not associated with separated modules, but, instead, appear to share a common and distributed neural substrate. Overall, this study introduces a versatile framework to isolate, in the brain activity, the distributed representations of linguistic constructs.
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive useful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings o…
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
Zuckerman Mind Brain Behavior Institute, Columbia University（扎克曼脑行为研究所，哥伦比亚大学）；Department of Electrical Engineering, Columbia University（电气工程系，哥伦比亚大学）；Department of Computer Science, Columbia University（计算机科学系，哥伦比亚大学）
A fundamental question in neurolinguistics concerns the brain regions involved in syntactic and semantic processing during speech comprehension, both at the lexical (word processing) and supra-lexical levels (sentence and discourse processing). To what extent are these regions separated or intertwined? To address this question, we trained a lexical language model, Glove, and a supra-lexical language model, GPT-2, on a text corpus from which we selectively removed either syntactic or semantic information. We then assessed to what extent these information-restricted models were able to predict t…
Northeastern University（东北大学）；University of Amsterdam（阿姆斯特丹大学）
Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to learn disentangled representations by identifying existing subnetworks within pretrained models that encode distinct, complementary aspect representations. Concretely, we learn binary masks over transformer weights or hidden units to uncover subsets of features that correlate with a specific factor of variation; this eliminates the need to train a disentangled…
Evaluation metrics are a key ingredient for progress of text generation systems. In recent years, several BERT-based evaluation metrics have been proposed (including BERTScore, MoverScore, BLEURT, etc.) which correlate much better with human assessment of text generation quality than BLEU or ROUGE, invented two decades ago. However, little is known what these metrics, which are based on black-box language model representations, actually capture (it is typically assumed they model semantic similarity). In this work, we use a simple regression based global explainability technique to disentangle…
University of Copenhagen（哥本哈根大学）；ETH Zurich（苏黎世联邦理工学院）；IT University of Copenhagen（哥本哈根信息技术大学）
Cognitively inspired NLP leverages human-derived data to teach machines about language processing mechanisms. Recently, neural networks have been augmented with behavioral data to solve a range of NLP tasks spanning syntax and semantics. We are the first to exploit neuroscientific data, namely electroencephalography (EEG), to inform a neural attention model about language processing of the human brain. The challenge in working with EEG data is that features are exceptionally rich and need extensive pre-processing to isolate signals specific to text processing. We devise a method for finding su…
McGovern Medical School, UTHealth（UTHealth麦戈文医学院）；Texas Institute for Restorative Neurotechnologies, UTHealth（UTHealth德克萨斯修复神经技术研究所）
A comprehensive model of natural language processing in the brain must accommodate four components: representations, operations, structures and encoding. It further requires a principled account of how these components mechanistically, and causally, relate to each another. While previous models have isolated regions of interest for structure-building and lexical access, many gaps remain with respect to bridging distinct scales of neural complexity. By expanding existing accounts of how neural oscillations can index various linguistic processes, this article proposes a neurocomputational archit…
Several popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the efficacy of task-specific learned Transformer representations. In this work, we explore transfer learning from representations learned for ten popular natural language processing tasks (two syntactic and eight semantic) for predicting brain responses from two diverse datasets: Pereira (subjects reading sentences from paragraphs) and Narratives (subjects listening to the spoken s…
A computational system implemented exclusively through the spiking of neurons was recently shown capable of syntax, that is, of carrying out the dependency parsing of simple English sentences. We address two of the most important questions left open by that work: constituency (the identification of key parts of the sentence such as the verb phrase) and the processing of dependent sentences, especially center-embedded ones. We show that these two aspects of language can also be implemented by neurons and synapses in a way that is compatible with what is known, or widely believed, about the stru…
How Syntax Specialization Emerges in Language Models
Department of Linguistics and Modern Languages, The Chinese University of Hong Kong（香港中文大学语言学与现代语言系）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Brain and Mind Institute, The Chinese University of Hong Kong（香港中文大学脑科学与心灵研究所）
Northwestern Polytechnical University（西北工业大学）；University of Georgia（佐治亚大学）；Athens Academy（雅典学院）
Linking computational natural language processing (NLP) models and neural responses to language in the human brain on the one hand facilitates the effort towards disentangling the neural representations underpinning language perception, on the other hand provides neurolinguistics evidence to evaluate and improve NLP models. Mappings of an NLP model's representations of and the brain activities evoked by linguistic input are typically deployed to reveal this symbiosis. However, two critical problems limit its advancement: 1) The model's representations (artificial neurons, ANs) rely on layer-le…
Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain
Peking University（北京大学）；Zhejiang University（浙江大学）；Beijing Language and Culture University（北京语言大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
University Hospital Hamburg（汉堡大学医院）；University Hospital Erlangen（埃尔兰根大学医院）；University Erlangen-Nuremberg（埃尔兰根-纽伦堡大学）
How do humans learn language, and can the first language be learned at all? These fundamental questions are still hotly debated. In contemporary linguistics, there are two major schools of thought that give completely opposite answers. According to Chomsky's theory of universal grammar, language cannot be learned because children are not exposed to sufficient data in their linguistic environment. In contrast, usage-based models of language assume a profound relationship between language structure and language use. In particular, contextual mental processing and mental representations are assum…
