Brains and algorithms partially converge in natural language processing

Deep learning algorithms trained to predict masked words from large amount of text have recently been shown to generate activations similar to those of the human brain. However, what drives this similarity remains currently unknown. Here, we systematically compare a variety of deep language models to identify the computational principles that lead them to generate brain-like representations of sentences. Specifically, we analyze the brain responses to 400 isolated sentences in a large cohort of 102 subjects, each recorded for two hours with functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG). We then test where and when each of these algorithms maps onto the brain responses. Finally,…

• AN
  Agence Nationale de la Recherche

  Awards: ANR-17-EURE-, ANR-17-EURE-0017, 17-EURE-0017, ANR-17
• FF
  Fondation Fyssen

  Awards: 17-EURE-0017, ANR-17-EURE-0017