Aligning context-based statistical models of language with brain activity during reading
Leila Wehbea b c d, Ashish Vaswanie f, Kevin K. Knighte f, Tom M. Mitchella b c d
- aCenter for the Neural Basis of Computation , Carnegie Mellon University , Pittsburgh , PA
- bMachine Learning Department , Carnegie Mellon University , Pittsburgh , PA
- cCenter for the Neural Basis of Computation, Carnegie Mellon University, Pittsburgh, PA
- dMachine Learning Department, Carnegie Mellon University, Pittsburgh, PA
- eInformation Sciences Institute , University of Southern California , Los Angeles , CA
- fInformation Sciences Institute, University of Southern California, Los Angeles, CA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Many statistical models for natural language processing exist, including context-based neural networks that (1) model the previously seen context as a latent feature vector, (2) integrate successive words into the context using some learned representation (embedding), and (3) compute output probabilities for incoming words given the context.On the other hand, brain imaging studies have suggested that during reading, the brain (a) continuously builds a context from the successive words and every time it encounters a word it (b) fetches its properties from memory and (c) integrates it with the previous context with a degree of effort that is inversely proportional to how probable the word is.This hints to a parallelism between the neural networks and the brain in modeling context (1 and a), representing the incoming words (2 and b) and integrating it (3 and c).We explore this parallelism to better understand the brain processes and the neural networks representations.We study the alignment between the latent vectors used by neural networks and brain activity observed via Magnetoencephalography (MEG) when subjects read a story.For that purpose we apply the neural network to the same text the subjects are reading, and explore the ability of these three vector representations to predict the observed word-by-word brain activity.Our novel results show that: before a new word i is read, brain activity is well predicted by the neural network latent representation of context and the predictability decreases as the brain integrates the word and changes its own representation of context.Secondly, the neural network embedding of word i can predict the MEG activity when word i is presented to the subject, revealing that it is correlated with the brain's own representation of word i.Moreover, we obtain that the activity is predicted in different regions of the brain with varying delay.The delay is consistent with the placement of each region on the processing pathway that starts in the visual cortex and moves to higher level regions.Finally, we show that the output probability computed by the neural networks agrees with the brain's own assessment of the probability of word i, as it can be used to predict the brain activity after the word i's properties have been fetched from memory and the brain is in the process of integrating it into the context.
TL;DRThe novel results show that before a new word i is read, brain activity is well predicted by the neural network latent representation of context and the predictability decreases as the brain integrates the word and changes its own representations of context. (Semantic Scholar)