Understanding and Improving Word Embeddings through a Neuroscientific Lens
Sam Fereidooni, Viola Mocz, Dragomir Radev, Marvin M. Chun
The paper investigates whether word embeddings align with brain representations and improves them using brain features, showing increased coherence with human semantic judgments.
bioRxiv · Sep 18, 2020 · PreprintNeuroscience