A brain–computer interface that decodes continuous language from non-invasive recordings
would have many scientific and practical applications. Currently, however, non-invasive …

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 …

The neuroscience of perception has recently been revolutionized with an integrative
modeling approach in which computation, brain function, and behavior are linked across …

Deep language algorithms, like GPT-2, have demonstrated remarkable abilities to process
text, and now constitute the backbone of automatic translation, summarization and dialogue …

State-of-the-art brain-to-text systems have achieved great success in decoding language
directly from brain signals using neural networks. However, current approaches are limited …

Word embeddings are vectorial semantic representations built with either counting or
predicting techniques aimed at capturing shades of meaning from word co-occurrences …

What information from an act of sentence understanding is robustly represented in the
human brain? We investigate this question by comparing sentence encoding models on a …

Deep learning has recently allowed substantial progress in language tasks such as
translation and completion. Do such models process language similarly to humans, and is …

The neuroscience of perception has recently been revolutionized with an integrative
modeling approach in which computation, brain function, and behavior are linked across …

Deep learning (DL) is increasingly viewed as a foundational methodology for advancing
Artificial Intelligence (AI). However, its interpretability remains limited, and it often …