A Framework for Decoding Event-Related Potentials from Text
Shaorong Yan, Aaron Steven White
February 2019
 

We propose a novel framework for modeling event-related potentials (ERPs) collected during reading that couples pre-trained convolutional decoders with a language model. Using this framework, we compare the abilities of a variety of existing and novel sentence processing models to reconstruct ERPs. We find that modern contextual word embeddings underperform surprisal-based models but that, combined, the two outperform either on its own.
Format: [ pdf ]
Reference: lingbuzz/004497
(please use that when you cite this article)
Published in:
keywords: sentence processing, event related potentials, electroencephalography, convolutional neural networks, semantics, syntax
previous versions: v2 [February 2019]
v1 [February 2019]
Downloaded:145 times

 

[ edit this article | back to article list ]