Litcius/Paper detail

SyntaxGym: An Online Platform for Targeted Evaluation of Language Models

Jon Gauthier, Jennifer Hu, Ethan Wilcox, Peng Qian, Roger Lévy

202065 citationsDOIOpen Access PDF

Abstract

Targeted syntactic evaluations have yielded insights into the generalizations learned by neural network language models. However, this line of research requires an uncommon confluence of skills: both the theoretical knowledge needed to design controlled psycholinguistic experiments, and the technical proficiency needed to train and deploy large-scale language models. We present SyntaxGym, an online platform designed to make targeted evaluations accessible to both experts in NLP and linguistics, reproducible across computing environments, and standardized following the norms of psycholinguistic experimental design. This paper releases two tools of independent value for the computational linguistics community:

Topics & Concepts

Computer scienceInferenceVisualizationArtificial intelligenceNatural language processingProcess (computing)Computational linguisticsProgramming languageTopic ModelingNatural Language Processing TechniquesText Readability and Simplification
SyntaxGym: An Online Platform for Targeted Evaluation of Language Models | Litcius