@inproceedings{newman-etal-2021-refining,
title = "Refining Targeted Syntactic Evaluation of Language Models",
author = "Newman, Benjamin and
Ang, Kai-Siang and
Gong, Julia and
Hewitt, John",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.290",
doi = "10.18653/v1/2021.naacl-main.290",
pages = "3710--3723",
abstract = "Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models{'} syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb{'}s conjugation. The method evaluates whether language models rate each grammatical sentence as more likely than its ungrammatical counterpart. We identify two distinct goals for TSE. First, evaluating the systematicity of a language model{'}s syntactic knowledge: given a sentence, can it conjugate arbitrary verbs correctly? Second, evaluating a model{'}s likely behavior: given a sentence, does the model concentrate its probability mass on correctly conjugated verbs, even if only on a subset of the possible verbs? We argue that current implementations of TSE do not directly capture either of these goals, and propose new metrics to capture each goal separately. Under our metrics, we find that TSE overestimates systematicity of language models, but that models score up to 40{\%} better on verbs that they predict are likely in context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="newman-etal-2021-refining">
<titleInfo>
<title>Refining Targeted Syntactic Evaluation of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Newman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Siang</namePart>
<namePart type="family">Ang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Hewitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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 evaluation of subject-verb number agreement in English (TSE) evaluates language models’ syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb’s conjugation. The method evaluates whether language models rate each grammatical sentence as more likely than its ungrammatical counterpart. We identify two distinct goals for TSE. First, evaluating the systematicity of a language model’s syntactic knowledge: given a sentence, can it conjugate arbitrary verbs correctly? Second, evaluating a model’s likely behavior: given a sentence, does the model concentrate its probability mass on correctly conjugated verbs, even if only on a subset of the possible verbs? We argue that current implementations of TSE do not directly capture either of these goals, and propose new metrics to capture each goal separately. Under our metrics, we find that TSE overestimates systematicity of language models, but that models score up to 40% better on verbs that they predict are likely in context.</abstract>
<identifier type="citekey">newman-etal-2021-refining</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.290</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.290</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3710</start>
<end>3723</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refining Targeted Syntactic Evaluation of Language Models
%A Newman, Benjamin
%A Ang, Kai-Siang
%A Gong, Julia
%A Hewitt, John
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F newman-etal-2021-refining
%X Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models’ syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb’s conjugation. The method evaluates whether language models rate each grammatical sentence as more likely than its ungrammatical counterpart. We identify two distinct goals for TSE. First, evaluating the systematicity of a language model’s syntactic knowledge: given a sentence, can it conjugate arbitrary verbs correctly? Second, evaluating a model’s likely behavior: given a sentence, does the model concentrate its probability mass on correctly conjugated verbs, even if only on a subset of the possible verbs? We argue that current implementations of TSE do not directly capture either of these goals, and propose new metrics to capture each goal separately. Under our metrics, we find that TSE overestimates systematicity of language models, but that models score up to 40% better on verbs that they predict are likely in context.
%R 10.18653/v1/2021.naacl-main.290
%U https://aclanthology.org/2021.naacl-main.290
%U https://doi.org/10.18653/v1/2021.naacl-main.290
%P 3710-3723
Markdown (Informal)
[Refining Targeted Syntactic Evaluation of Language Models](https://aclanthology.org/2021.naacl-main.290) (Newman et al., NAACL 2021)
ACL
- Benjamin Newman, Kai-Siang Ang, Julia Gong, and John Hewitt. 2021. Refining Targeted Syntactic Evaluation of Language Models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3710–3723, Online. Association for Computational Linguistics.