@inproceedings{gauthier-etal-2020-syntaxgym,
title = "{S}yntax{G}ym: An Online Platform for Targeted Evaluation of Language Models",
author = "Gauthier, Jon and
Hu, Jennifer and
Wilcox, Ethan and
Qian, Peng and
Levy, Roger",
editor = "Celikyilmaz, Asli and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-demos.10",
doi = "10.18653/v1/2020.acl-demos.10",
pages = "70--76",
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: 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gauthier-etal-2020-syntaxgym">
<titleInfo>
<title>SyntaxGym: An Online Platform for Targeted Evaluation of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Gauthier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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: 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.</abstract>
<identifier type="citekey">gauthier-etal-2020-syntaxgym</identifier>
<identifier type="doi">10.18653/v1/2020.acl-demos.10</identifier>
<location>
<url>https://aclanthology.org/2020.acl-demos.10</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>70</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SyntaxGym: An Online Platform for Targeted Evaluation of Language Models
%A Gauthier, Jon
%A Hu, Jennifer
%A Wilcox, Ethan
%A Qian, Peng
%A Levy, Roger
%Y Celikyilmaz, Asli
%Y Wen, Tsung-Hsien
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F gauthier-etal-2020-syntaxgym
%X 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: 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.
%R 10.18653/v1/2020.acl-demos.10
%U https://aclanthology.org/2020.acl-demos.10
%U https://doi.org/10.18653/v1/2020.acl-demos.10
%P 70-76
Markdown (Informal)
[SyntaxGym: An Online Platform for Targeted Evaluation of Language Models](https://aclanthology.org/2020.acl-demos.10) (Gauthier et al., ACL 2020)
ACL