218 citations · 315 across the 11 of their papers we have counts for
3 papers · 2 filters
Disentangling Syntax and Semantics in the Brain with Deep Networks
Charlotte Caucheteux, Alexandre Gramfort, Jean-Remi King
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 remain…
Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech
Juliette Millet, Jean-Remi King
Our ability to comprehend speech remains, to date, unrivaled by deep learning models. This feat could result from the brain's ability to fine-tune generic sound representations for…
Can RNNs learn Recursive Nested Subject-Verb Agreements?
Yair Lakretz, Théo Desbordes, Jean-Rémi King +3
One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remain…