@inproceedings{chen-gao-2022-curriculum,
title = "Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding",
author = "Chen, Zeming and
Gao, Qiyue",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.234",
doi = "10.18653/v1/2022.naacl-main.234",
pages = "3204--3219",
abstract = "In the age of large transformer language models, linguistic evaluation play an important role in diagnosing models{'} abilities and limitations on natural language understanding. However, current evaluation methods show some significant shortcomings. In particular, they do not provide insight into how well a language model captures distinct linguistic skills essential for language understanding and reasoning. Thus they fail to effectively map out the aspects of language understanding that remain challenging to existing models, which makes it hard to discover potential limitations in models and datasets. In this paper, we introduce Curriculum as a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. Curriculum contains a collection of datasets that covers 36 types of major linguistic phenomena and an evaluation procedure for diagnosing how well a language model captures reasoning skills for distinct types of linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality. In addition, our experiments provide insight into the limitation of existing benchmark datasets and state-of-the-art models that may encourage future research on re-designing datasets, model architectures, and learning objectives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-gao-2022-curriculum">
<titleInfo>
<title>Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zeming</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiyue</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the age of large transformer language models, linguistic evaluation play an important role in diagnosing models’ abilities and limitations on natural language understanding. However, current evaluation methods show some significant shortcomings. In particular, they do not provide insight into how well a language model captures distinct linguistic skills essential for language understanding and reasoning. Thus they fail to effectively map out the aspects of language understanding that remain challenging to existing models, which makes it hard to discover potential limitations in models and datasets. In this paper, we introduce Curriculum as a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. Curriculum contains a collection of datasets that covers 36 types of major linguistic phenomena and an evaluation procedure for diagnosing how well a language model captures reasoning skills for distinct types of linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality. In addition, our experiments provide insight into the limitation of existing benchmark datasets and state-of-the-art models that may encourage future research on re-designing datasets, model architectures, and learning objectives.</abstract>
<identifier type="citekey">chen-gao-2022-curriculum</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.234</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.234</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3204</start>
<end>3219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding
%A Chen, Zeming
%A Gao, Qiyue
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F chen-gao-2022-curriculum
%X In the age of large transformer language models, linguistic evaluation play an important role in diagnosing models’ abilities and limitations on natural language understanding. However, current evaluation methods show some significant shortcomings. In particular, they do not provide insight into how well a language model captures distinct linguistic skills essential for language understanding and reasoning. Thus they fail to effectively map out the aspects of language understanding that remain challenging to existing models, which makes it hard to discover potential limitations in models and datasets. In this paper, we introduce Curriculum as a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. Curriculum contains a collection of datasets that covers 36 types of major linguistic phenomena and an evaluation procedure for diagnosing how well a language model captures reasoning skills for distinct types of linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality. In addition, our experiments provide insight into the limitation of existing benchmark datasets and state-of-the-art models that may encourage future research on re-designing datasets, model architectures, and learning objectives.
%R 10.18653/v1/2022.naacl-main.234
%U https://aclanthology.org/2022.naacl-main.234
%U https://doi.org/10.18653/v1/2022.naacl-main.234
%P 3204-3219
Markdown (Informal)
[Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding](https://aclanthology.org/2022.naacl-main.234) (Chen & Gao, NAACL 2022)
ACL