@inproceedings{goel-etal-2021-robustness,
title = "Robustness Gym: Unifying the {NLP} Evaluation Landscape",
author = "Goel, Karan and
Rajani, Nazneen Fatema and
Vig, Jesse and
Taschdjian, Zachary and
Bansal, Mohit and
R{\'e}, Christopher",
editor = "Sil, Avi and
Lin, Xi Victoria",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-demos.6",
doi = "10.18653/v1/2021.naacl-demos.6",
pages = "42--55",
abstract = "Despite impressive performance on standard benchmarks, natural language processing (NLP) models are often brittle when deployed in real-world systems. In this work, we identify challenges with evaluating NLP systems and propose a solution in the form of Robustness Gym (RG), a simple and extensible evaluation toolkit that unifies 4 standard evaluation paradigms: subpopulations, transformations, evaluation sets, and adversarial attacks. By providing a common platform for evaluation, RG enables practitioners to compare results from disparate evaluation paradigms with a single click, and to easily develop and share novel evaluation methods using a built-in set of abstractions. RG is under active development and we welcome feedback {\&} contributions from the community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goel-etal-2021-robustness">
<titleInfo>
<title>Robustness Gym: Unifying the NLP Evaluation Landscape</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karan</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazneen</namePart>
<namePart type="given">Fatema</namePart>
<namePart type="family">Rajani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Vig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Taschdjian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ré</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: Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</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>Despite impressive performance on standard benchmarks, natural language processing (NLP) models are often brittle when deployed in real-world systems. In this work, we identify challenges with evaluating NLP systems and propose a solution in the form of Robustness Gym (RG), a simple and extensible evaluation toolkit that unifies 4 standard evaluation paradigms: subpopulations, transformations, evaluation sets, and adversarial attacks. By providing a common platform for evaluation, RG enables practitioners to compare results from disparate evaluation paradigms with a single click, and to easily develop and share novel evaluation methods using a built-in set of abstractions. RG is under active development and we welcome feedback & contributions from the community.</abstract>
<identifier type="citekey">goel-etal-2021-robustness</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-demos.6</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-demos.6</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>42</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robustness Gym: Unifying the NLP Evaluation Landscape
%A Goel, Karan
%A Rajani, Nazneen Fatema
%A Vig, Jesse
%A Taschdjian, Zachary
%A Bansal, Mohit
%A Ré, Christopher
%Y Sil, Avi
%Y Lin, Xi Victoria
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F goel-etal-2021-robustness
%X Despite impressive performance on standard benchmarks, natural language processing (NLP) models are often brittle when deployed in real-world systems. In this work, we identify challenges with evaluating NLP systems and propose a solution in the form of Robustness Gym (RG), a simple and extensible evaluation toolkit that unifies 4 standard evaluation paradigms: subpopulations, transformations, evaluation sets, and adversarial attacks. By providing a common platform for evaluation, RG enables practitioners to compare results from disparate evaluation paradigms with a single click, and to easily develop and share novel evaluation methods using a built-in set of abstractions. RG is under active development and we welcome feedback & contributions from the community.
%R 10.18653/v1/2021.naacl-demos.6
%U https://aclanthology.org/2021.naacl-demos.6
%U https://doi.org/10.18653/v1/2021.naacl-demos.6
%P 42-55
Markdown (Informal)
[Robustness Gym: Unifying the NLP Evaluation Landscape](https://aclanthology.org/2021.naacl-demos.6) (Goel et al., NAACL 2021)
ACL
- Karan Goel, Nazneen Fatema Rajani, Jesse Vig, Zachary Taschdjian, Mohit Bansal, and Christopher Ré. 2021. Robustness Gym: Unifying the NLP Evaluation Landscape. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations, pages 42–55, Online. Association for Computational Linguistics.