@inproceedings{belz-etal-2021-reprogen,
title = "The {R}epro{G}en Shared Task on Reproducibility of Human Evaluations in {NLG}: Overview and Results",
author = "Belz, Anya and
Shimorina, Anastasia and
Agarwal, Shubham and
Reiter, Ehud",
editor = "Belz, Anya and
Fan, Angela and
Reiter, Ehud and
Sripada, Yaji",
booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",
month = aug,
year = "2021",
address = "Aberdeen, Scotland, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.inlg-1.24/",
doi = "10.18653/v1/2021.inlg-1.24",
pages = "249--258",
abstract = "The NLP field has recently seen a substantial increase in work related to reproducibility of results, and more generally in recognition of the importance of having shared definitions and practices relating to evaluation. Much of the work on reproducibility has so far focused on metric scores, with reproducibility of human evaluation results receiving far less attention. As part of a research programme designed to develop theory and practice of reproducibility assessment in NLP, we organised the first shared task on reproducibility of human evaluations, ReproGen 2021. This paper describes the shared task in detail, summarises results from each of the reproduction studies submitted, and provides further comparative analysis of the results. Out of nine initial team registrations, we received submissions from four teams. Meta-analysis of the four reproduction studies revealed varying degrees of reproducibility, and allowed very tentative first conclusions about what types of evaluation tend to have better reproducibility."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belz-etal-2021-reprogen">
<titleInfo>
<title>The ReproGen Shared Task on Reproducibility of Human Evaluations in NLG: Overview and Results</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">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Agarwal</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>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Natural Language Generation</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">Angela</namePart>
<namePart type="family">Fan</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">Yaji</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Aberdeen, Scotland, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The NLP field has recently seen a substantial increase in work related to reproducibility of results, and more generally in recognition of the importance of having shared definitions and practices relating to evaluation. Much of the work on reproducibility has so far focused on metric scores, with reproducibility of human evaluation results receiving far less attention. As part of a research programme designed to develop theory and practice of reproducibility assessment in NLP, we organised the first shared task on reproducibility of human evaluations, ReproGen 2021. This paper describes the shared task in detail, summarises results from each of the reproduction studies submitted, and provides further comparative analysis of the results. Out of nine initial team registrations, we received submissions from four teams. Meta-analysis of the four reproduction studies revealed varying degrees of reproducibility, and allowed very tentative first conclusions about what types of evaluation tend to have better reproducibility.</abstract>
<identifier type="citekey">belz-etal-2021-reprogen</identifier>
<identifier type="doi">10.18653/v1/2021.inlg-1.24</identifier>
<location>
<url>https://aclanthology.org/2021.inlg-1.24/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>249</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The ReproGen Shared Task on Reproducibility of Human Evaluations in NLG: Overview and Results
%A Belz, Anya
%A Shimorina, Anastasia
%A Agarwal, Shubham
%A Reiter, Ehud
%Y Belz, Anya
%Y Fan, Angela
%Y Reiter, Ehud
%Y Sripada, Yaji
%S Proceedings of the 14th International Conference on Natural Language Generation
%D 2021
%8 August
%I Association for Computational Linguistics
%C Aberdeen, Scotland, UK
%F belz-etal-2021-reprogen
%X The NLP field has recently seen a substantial increase in work related to reproducibility of results, and more generally in recognition of the importance of having shared definitions and practices relating to evaluation. Much of the work on reproducibility has so far focused on metric scores, with reproducibility of human evaluation results receiving far less attention. As part of a research programme designed to develop theory and practice of reproducibility assessment in NLP, we organised the first shared task on reproducibility of human evaluations, ReproGen 2021. This paper describes the shared task in detail, summarises results from each of the reproduction studies submitted, and provides further comparative analysis of the results. Out of nine initial team registrations, we received submissions from four teams. Meta-analysis of the four reproduction studies revealed varying degrees of reproducibility, and allowed very tentative first conclusions about what types of evaluation tend to have better reproducibility.
%R 10.18653/v1/2021.inlg-1.24
%U https://aclanthology.org/2021.inlg-1.24/
%U https://doi.org/10.18653/v1/2021.inlg-1.24
%P 249-258
Markdown (Informal)
[The ReproGen Shared Task on Reproducibility of Human Evaluations in NLG: Overview and Results](https://aclanthology.org/2021.inlg-1.24/) (Belz et al., INLG 2021)
ACL