Skip to content
conftrace_
2020 ACL ACL 2020

SyntaxGym: An Online Platform for Targeted Evaluation of Language Models

AbstractTargeted 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: 1. A website, syntaxgym.org, which centralizes the process of targeted syntactic evaluation and provides easy tools for analysis and visualization; 2. Two command-line tools, ‘syntaxgym‘ and ‘lm-zoo‘, which allow any user to reproduce targeted syntactic evaluations and general language model inference on their own machine.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Interdisciplinary and Natural Language Processing
📈 Trend Setter - Evaluation
🐣 Hot Topic Early Bird - computational linguistics

More from ACL 2020

All ACL 2020 papers →