Human Sentence Processing: Recurrence or Attention?
Danny Merkx, Stefan L. Frank
Abstract
Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks but little is known about its ability to model human language processing. We compare Transformer-and RNNbased language models' ability to account for measures of human reading effort. Our analysis shows Transformers to outperform RNNs in explaining self-paced reading times and neural activity during reading English sentences, challenging the widely held idea that human sentence processing involves recurrent and immediate processing and provides evidence for cue-based retrieval.
Topics & Concepts
Computer scienceSentenceTransformerRecurrent neural networkNatural language processingArtificial intelligenceSentence processingHuman languageReading (process)Language modelNatural languageArchitectureSpeech recognitionArtificial neural networkQuestion answeringLanguage understandingNeurobiology of Language and BilingualismText Readability and SimplificationTopic Modeling