Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns.

ABSTRACT: Contextual embeddings, derived from deep language models (DLMs), provide a continuous vectorial representation of language. This embedding space differs fundamentally from the symbolic representations posited by traditional psycholinguistics. We hypothesize that language areas in the human brain, similar to DLMs, rely on a continuous embedding space to represent language. To test this hypothesis, we densely record the neural activity patterns in the inferior frontal gyrus (IFG) of three participants using dense intracranial arrays while they listened to a 30-minute podcast. From these fine-grained spatiotemporal neural recordings, we derive a continuous vectorial representation for each word (i.e., a brain embedding) in each patient. Using stringent zero-shot mapping we demonstrate that br

SUBMITTER: Goldstein A 

PROVIDER: S-EPMC10980748 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature