@inproceedings{belz-thomson-2024-2024,
title = "The 2024 {R}epro{NLP} Shared Task on Reproducibility of Evaluations in {NLP}: Overview and Results",
author = "Belz, Anya and
Thomson, Craig",
editor = "Balloccu, Simone and
Belz, Anya and
Huidrom, Rudali and
Reiter, Ehud and
Sedoc, Joao and
Thomson, Craig",
booktitle = "Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.humeval-1.9",
pages = "91--105",
abstract = "This paper presents an overview of, and the results from, the 2024 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP{'}24), following on from three previous shared tasks on reproducibility of evaluations in NLP, ReproNLP{'}23, ReproGen{'}22 and ReproGen{'}21. This shared task series forms part of an ongoing research programme designed to develop theory and practice of reproducibility assessment in NLP and machine learning, against a backdrop of increasing recognition of the importance of reproducibility across the two fields. We describe the ReproNLP{'}24 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belz-thomson-2024-2024">
<titleInfo>
<title>The 2024 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: 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">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Rudali</namePart>
<namePart type="family">Huidrom</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">Joao</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an overview of, and the results from, the 2024 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP’24), following on from three previous shared tasks on reproducibility of evaluations in NLP, ReproNLP’23, ReproGen’22 and ReproGen’21. This shared task series forms part of an ongoing research programme designed to develop theory and practice of reproducibility assessment in NLP and machine learning, against a backdrop of increasing recognition of the importance of reproducibility across the two fields. We describe the ReproNLP’24 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results.</abstract>
<identifier type="citekey">belz-thomson-2024-2024</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.9</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>91</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The 2024 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: Overview and Results
%A Belz, Anya
%A Thomson, Craig
%Y Balloccu, Simone
%Y Belz, Anya
%Y Huidrom, Rudali
%Y Reiter, Ehud
%Y Sedoc, Joao
%Y Thomson, Craig
%S Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F belz-thomson-2024-2024
%X This paper presents an overview of, and the results from, the 2024 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP’24), following on from three previous shared tasks on reproducibility of evaluations in NLP, ReproNLP’23, ReproGen’22 and ReproGen’21. This shared task series forms part of an ongoing research programme designed to develop theory and practice of reproducibility assessment in NLP and machine learning, against a backdrop of increasing recognition of the importance of reproducibility across the two fields. We describe the ReproNLP’24 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results.
%U https://aclanthology.org/2024.humeval-1.9
%P 91-105
Markdown (Informal)
[The 2024 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: Overview and Results](https://aclanthology.org/2024.humeval-1.9) (Belz & Thomson, HumEval-WS 2024)
ACL