A Framework for Decoding Event-Related Potentials from Text
This work addresses decoding brain signals from text for neuroscience and computational linguistics, but it appears incremental as it builds on existing models and methods.
The authors tackled the problem of modeling event-related potentials (ERPs) during reading by proposing a framework that combines pre-trained convolutional decoders with a language model, finding that modern contextual word embeddings underperform surprisal-based models but their combination outperforms either alone.
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.