Article

Language processing in brains and deep neural networks: computational convergence and its limits

2020-07-04

Abstract excerpt

<h4> A bstract </h4> Deep Learning has recently led to major advances in natural language processing. Do these models process sentences similarly to humans, and is this similarity driven by specific principles? Using a variety of artificial neural networks, trained on image classification, word embedding, or language modeling, we evaluate whether their architectural and functional properties lead them to genera...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 685fe327-db3b-5b3b-9c1f-9b6969e0e9f1
DOI: 10.1101/2020.07.03.186288

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Language processing in brains and deep neural networks: computational convergence and its limitsDOI 10.1101/2020.07.03.186288Read

Lexical semantic content, not syntactic structure, is the main contributor to ANN-brain similarity of fMRI responses in the language networkSemantic proximity Read

The neural architecture of language: Integrative modeling converges on predictive processingSemantic proximity Read

Shared functional specialization in transformer-based language models and the human brainSemantic proximity Read

Dimensionality and ramping: Signatures of sentence integration in the dynamics of brains and deep language modelsSemantic proximity Read

Driving and suppressing the human language network using large language modelsSemantic proximity Read

A unifying computational account of temporal context effects in language across the human cortexSemantic proximity Read

Neurocognitive Mechanisms Supporting the Generalization of Concepts Across LanguagesSemantic proximity Read

Can computers understand words like humans do? Comparable semantic representation in neural and computer systemsSemantic proximity Read

Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language ModelsSemantic proximity Read

Thinking ahead: spontaneous prediction in context as a keystone of language in humans and machinesSemantic proximity Read

Linguistic inputs must be syntactically parsable to fully engage the language networkSemantic proximity Read

NiCLIP: Neuroimaging contrastive language-image pretraining model for predicting text from brain activation imagesSemantic proximity Read