@inproceedings{bhatt-etal-2021-case,
title = "A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of {NLP} Systems Using Checklist",
author = "Bhatt, Shaily and
Jain, Rahul and
Dandapat, Sandipan and
Sitaram, Sunayana",
editor = "Belz, Anya and
Agarwal, Shubham and
Graham, Yvette and
Reiter, Ehud and
Shimorina, Anastasia",
booktitle = "Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.humeval-1.14/",
pages = "120--130",
abstract = "Despite state-of-the-art performance, NLP systems can be fragile in real-world situations. This is often due to insufficient understanding of the capabilities and limitations of models and the heavy reliance on standard evaluation benchmarks. Research into non-standard evaluation to mitigate this brittleness is gaining increasing attention. Notably, the behavioral testing principle {\textquoteleft}Checklist', which decouples testing from implementation revealed significant failures in state-of-the-art models for multiple tasks. In this paper, we present a case study of using Checklist in a practical scenario. We conduct experiments for evaluating an offensive content detection system and use a data augmentation technique for improving the model using insights from Checklist. We lay out the challenges and open questions based on our observations of using Checklist for human-in-loop evaluation and improvement of NLP systems. Disclaimer: The paper contains examples of content with offensive language. The examples do not represent the views of the authors or their employers towards any person(s), group(s), practice(s), or entity/entities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhatt-etal-2021-case">
<titleInfo>
<title>A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of NLP Systems Using Checklist</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaily</namePart>
<namePart type="family">Bhatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Dandapat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</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 state-of-the-art performance, NLP systems can be fragile in real-world situations. This is often due to insufficient understanding of the capabilities and limitations of models and the heavy reliance on standard evaluation benchmarks. Research into non-standard evaluation to mitigate this brittleness is gaining increasing attention. Notably, the behavioral testing principle ‘Checklist’, which decouples testing from implementation revealed significant failures in state-of-the-art models for multiple tasks. In this paper, we present a case study of using Checklist in a practical scenario. We conduct experiments for evaluating an offensive content detection system and use a data augmentation technique for improving the model using insights from Checklist. We lay out the challenges and open questions based on our observations of using Checklist for human-in-loop evaluation and improvement of NLP systems. Disclaimer: The paper contains examples of content with offensive language. The examples do not represent the views of the authors or their employers towards any person(s), group(s), practice(s), or entity/entities.</abstract>
<identifier type="citekey">bhatt-etal-2021-case</identifier>
<location>
<url>https://aclanthology.org/2021.humeval-1.14/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>120</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of NLP Systems Using Checklist
%A Bhatt, Shaily
%A Jain, Rahul
%A Dandapat, Sandipan
%A Sitaram, Sunayana
%Y Belz, Anya
%Y Agarwal, Shubham
%Y Graham, Yvette
%Y Reiter, Ehud
%Y Shimorina, Anastasia
%S Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F bhatt-etal-2021-case
%X Despite state-of-the-art performance, NLP systems can be fragile in real-world situations. This is often due to insufficient understanding of the capabilities and limitations of models and the heavy reliance on standard evaluation benchmarks. Research into non-standard evaluation to mitigate this brittleness is gaining increasing attention. Notably, the behavioral testing principle ‘Checklist’, which decouples testing from implementation revealed significant failures in state-of-the-art models for multiple tasks. In this paper, we present a case study of using Checklist in a practical scenario. We conduct experiments for evaluating an offensive content detection system and use a data augmentation technique for improving the model using insights from Checklist. We lay out the challenges and open questions based on our observations of using Checklist for human-in-loop evaluation and improvement of NLP systems. Disclaimer: The paper contains examples of content with offensive language. The examples do not represent the views of the authors or their employers towards any person(s), group(s), practice(s), or entity/entities.
%U https://aclanthology.org/2021.humeval-1.14/
%P 120-130
Markdown (Informal)
[A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of NLP Systems Using Checklist](https://aclanthology.org/2021.humeval-1.14/) (Bhatt et al., HumEval 2021)
ACL