@inproceedings{belz-etal-2023-non,
title = "Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in {NLP}",
author = "Belz, Anya and
Thomson, Craig and
Reiter, Ehud and
Mille, Simon",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.226",
doi = "10.18653/v1/2023.findings-acl.226",
pages = "3676--3687",
abstract = "Human evaluation is widely regarded as the litmus test of quality in NLP. A basic requirementof all evaluations, but in particular where they are used for meta-evaluation, is that they should support the same conclusions if repeated. However, the reproducibility of human evaluations is virtually never queried, let alone formally tested, in NLP which means that their repeatability and the reproducibility of their results is currently an open question. This focused contribution reports our review of human evaluation experiments reported in NLP papers over the past five years which we assessed in terms oftheir ability to be rerun. Overall, we estimatethat just 5{\%} of human evaluations are repeatable in the sense that (i) there are no prohibitivebarriers to repetition, and (ii) sufficient information about experimental design is publicly available for rerunning them. Our estimate goesup to about 20{\%} when author help is sought. We complement this investigation with a survey of results concerning the reproducibilityof human evaluations where those are repeatable in the first place. Here we find worryinglylow degrees of reproducibility, both in terms ofsimilarity of scores and of findings supportedby them. We summarise what insights can begleaned so far regarding how to make humanevaluations in NLP more repeatable and morereproducible.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belz-etal-2023-non">
<titleInfo>
<title>Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human evaluation is widely regarded as the litmus test of quality in NLP. A basic requirementof all evaluations, but in particular where they are used for meta-evaluation, is that they should support the same conclusions if repeated. However, the reproducibility of human evaluations is virtually never queried, let alone formally tested, in NLP which means that their repeatability and the reproducibility of their results is currently an open question. This focused contribution reports our review of human evaluation experiments reported in NLP papers over the past five years which we assessed in terms oftheir ability to be rerun. Overall, we estimatethat just 5% of human evaluations are repeatable in the sense that (i) there are no prohibitivebarriers to repetition, and (ii) sufficient information about experimental design is publicly available for rerunning them. Our estimate goesup to about 20% when author help is sought. We complement this investigation with a survey of results concerning the reproducibilityof human evaluations where those are repeatable in the first place. Here we find worryinglylow degrees of reproducibility, both in terms ofsimilarity of scores and of findings supportedby them. We summarise what insights can begleaned so far regarding how to make humanevaluations in NLP more repeatable and morereproducible.</abstract>
<identifier type="citekey">belz-etal-2023-non</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.226</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.226</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3676</start>
<end>3687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in NLP
%A Belz, Anya
%A Thomson, Craig
%A Reiter, Ehud
%A Mille, Simon
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F belz-etal-2023-non
%X Human evaluation is widely regarded as the litmus test of quality in NLP. A basic requirementof all evaluations, but in particular where they are used for meta-evaluation, is that they should support the same conclusions if repeated. However, the reproducibility of human evaluations is virtually never queried, let alone formally tested, in NLP which means that their repeatability and the reproducibility of their results is currently an open question. This focused contribution reports our review of human evaluation experiments reported in NLP papers over the past five years which we assessed in terms oftheir ability to be rerun. Overall, we estimatethat just 5% of human evaluations are repeatable in the sense that (i) there are no prohibitivebarriers to repetition, and (ii) sufficient information about experimental design is publicly available for rerunning them. Our estimate goesup to about 20% when author help is sought. We complement this investigation with a survey of results concerning the reproducibilityof human evaluations where those are repeatable in the first place. Here we find worryinglylow degrees of reproducibility, both in terms ofsimilarity of scores and of findings supportedby them. We summarise what insights can begleaned so far regarding how to make humanevaluations in NLP more repeatable and morereproducible.
%R 10.18653/v1/2023.findings-acl.226
%U https://aclanthology.org/2023.findings-acl.226
%U https://doi.org/10.18653/v1/2023.findings-acl.226
%P 3676-3687
Markdown (Informal)
[Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in NLP](https://aclanthology.org/2023.findings-acl.226) (Belz et al., Findings 2023)
ACL