Investigating the Timescales of Language Processing with EEG and Language Models
This work addresses the problem of understanding fine-timescale interactions between artificial language models and brain responses during language comprehension for researchers in cognitive neuroscience and computational linguistics, but it is incremental as it builds on existing methods like TRFs and LDA.
This study investigated the temporal dynamics of language processing by aligning word representations from a pre-trained transformer-based language model with EEG data using a Temporal Response Function (TRF) model, revealing patterns in how different model layers contribute to lexical and compositional processing and insights into syntactic mechanisms through part-of-speech analysis.
This study explores the temporal dynamics of language processing by examining the alignment between word representations from a pre-trained transformer-based language model, and EEG data. Using a Temporal Response Function (TRF) model, we investigate how neural activity corresponds to model representations across different layers, revealing insights into the interaction between artificial language models and brain responses during language comprehension. Our analysis reveals patterns in TRFs from distinct layers, highlighting varying contributions to lexical and compositional processing. Additionally, we used linear discriminant analysis (LDA) to isolate part-of-speech (POS) representations, offering insights into their influence on neural responses and the underlying mechanisms of syntactic processing. These findings underscore EEG's utility for probing language processing dynamics with high temporal resolution. By bridging artificial language models and neural activity, this study advances our understanding of their interaction at fine timescales.