Researchers have, for the first time, decoded and predicted the brain activity patterns of word meanings within sentences, an advance that may help brain injury and stroke patients communicate better. The study used functional magnetic resonance imaging (fMRI) to measure human brain activation where researchers successfully predicted what the brain patterns would be for new sentences.

“Using fMRI data, we wanted to know if given a whole sentence, can we filter out what the brain’s representation of a word is — that is to say, can we break the sentence apart into its word components, then take the components and predict what they would look like in a new sentence,” said Andrew Anderson from University of Rochester in the US.

“We found that we can predict brain activity patterns — not perfectly (on average 70 per cent correct), but significantly better than chance,” said Anderson.

The study makes key advances towards understanding how information is represented throughout the brain.

“We introduced a method for predicting the neural patterns of words within sentences — which is a more complex problem than has been addressed by previous studies, which have almost all focused on single words,” said Anderson.

comment COMMENT NOW