Litcius/Paper detail

Context Limitations Make Neural Language Models More Human-Like

Tatsuki Kuribayashi, Yohei Oseki, Ana Brassard, Kentaro Inui

202229 citationsDOIOpen Access PDF

Abstract

Language models (LMs) have been used in cognitive modeling as well as engineering studies—they compute information-theoretic complexity metrics that simulate humans' cognitive load during reading.This study highlights a limitation of modern neural LMs as the model of choice for this purpose: there is a discrepancy between their context access capacities and that of humans.Our results showed that constraining the LMs' context access improved their simulation of human reading behavior.We also showed that LM-human gaps in context access were associated with specific syntactic constructions; incorporating syntactic biases into LMs' context access might enhance their cognitive plausibility.

Topics & Concepts

Computer scienceContext (archaeology)Reading (process)CognitionContext modelArtificial intelligenceLanguage modelNatural language processingCognitive scienceMachine learningLinguisticsPsychologyBiologyObject (grammar)NeurosciencePaleontologyPhilosophyTopic ModelingText Readability and Simplification
Context Limitations Make Neural Language Models More Human-Like | Litcius