Can Computers Understand Words Like Humans Do? Comparable Semantic Representation in Neural and Computer Systems

Semantic representation has been studied independently in neuroscience and computer science. A deep understanding of human neural computations and the revolution to strong artificial intelligence appeal for a joint force in the language domain. To investigate comparable representational formats of lexical semantics between these two complex systems, we used fine temporal resolution neural recordings to create a novel open dataset and innovated analysis methods. Specifically, we evaluated three natural language processing (NLP) models with electroencephalography (EEG) recordings under a semantic priming paradigm. With our novel single-trial analysis method, we found semantic representations generated from computational models significantly correlated with EEG responses at an early stage of a typical semantic processing time window in a two -word semantic priming paradigm. Moreover, three representative computational models differentially predicted EEG responses along the dynamics of word processing. Our study thus developed an objective biomarker for assessing human-like computation in computational models. Our novel framework trailblazed a promising way to bridge across disciplines in the investigation of higher-order cognitive functions in human and artificial intelligence.