English

A Framework for Decoding Event-Related Potentials from Text

Computation and Language 2019-04-03 v2

Abstract

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.

Keywords

Cite

@article{arxiv.1902.10296,
  title  = {A Framework for Decoding Event-Related Potentials from Text},
  author = {Shaorong Yan and Aaron Steven White},
  journal= {arXiv preprint arXiv:1902.10296},
  year   = {2019}
}
R2 v1 2026-06-23T07:52:30.235Z