@inproceedings{mondella-etal-2024-reprohum,
title = "{R}epro{H}um {\#}0892-01: The painful route to consistent results: A reproduction study of human evaluation in {NLG}",
author = "Mondella, Irene and
Lai, Huiyuan and
Nissim, Malvina",
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-1.24",
pages = "261--268",
abstract = "In spite of the core role human judgement plays in evaluating the performance of NLP systems, the way human assessments are elicited in NLP experiments, and to some extent the nature of human judgement itself, pose challenges to the reliability and validity of human evaluation. In the context of the larger ReproHum project, aimed at running large scale multi-lab reproductions of human judgement, we replicated the understandability assessment by humans on several generated outputs of simplified text described in the paper {``}Neural Text Simplification of Clinical Letters with a Domain Specific Phrase Table{''} by Shardlow and Nawaz, appeared in the Proceedings of ACL 2019. Although we had to implement a series of modifications compared to the original study, which were necessary to run our human evaluation on exactly the same data, we managed to collect assessments and compare results with the original study. We obtained results consistent with those of the reference study, confirming their findings. The paper is complete with as much information as possible to foster and facilitate future reproduction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mondella-etal-2024-reprohum">
<titleInfo>
<title>ReproHum #0892-01: The painful route to consistent results: A reproduction study of human evaluation in NLG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Mondella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huiyuan</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</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>In spite of the core role human judgement plays in evaluating the performance of NLP systems, the way human assessments are elicited in NLP experiments, and to some extent the nature of human judgement itself, pose challenges to the reliability and validity of human evaluation. In the context of the larger ReproHum project, aimed at running large scale multi-lab reproductions of human judgement, we replicated the understandability assessment by humans on several generated outputs of simplified text described in the paper “Neural Text Simplification of Clinical Letters with a Domain Specific Phrase Table” by Shardlow and Nawaz, appeared in the Proceedings of ACL 2019. Although we had to implement a series of modifications compared to the original study, which were necessary to run our human evaluation on exactly the same data, we managed to collect assessments and compare results with the original study. We obtained results consistent with those of the reference study, confirming their findings. The paper is complete with as much information as possible to foster and facilitate future reproduction.</abstract>
<identifier type="citekey">mondella-etal-2024-reprohum</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.24</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>261</start>
<end>268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproHum #0892-01: The painful route to consistent results: A reproduction study of human evaluation in NLG
%A Mondella, Irene
%A Lai, Huiyuan
%A Nissim, Malvina
%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 mondella-etal-2024-reprohum
%X In spite of the core role human judgement plays in evaluating the performance of NLP systems, the way human assessments are elicited in NLP experiments, and to some extent the nature of human judgement itself, pose challenges to the reliability and validity of human evaluation. In the context of the larger ReproHum project, aimed at running large scale multi-lab reproductions of human judgement, we replicated the understandability assessment by humans on several generated outputs of simplified text described in the paper “Neural Text Simplification of Clinical Letters with a Domain Specific Phrase Table” by Shardlow and Nawaz, appeared in the Proceedings of ACL 2019. Although we had to implement a series of modifications compared to the original study, which were necessary to run our human evaluation on exactly the same data, we managed to collect assessments and compare results with the original study. We obtained results consistent with those of the reference study, confirming their findings. The paper is complete with as much information as possible to foster and facilitate future reproduction.
%U https://aclanthology.org/2024.humeval-1.24
%P 261-268
Markdown (Informal)
[ReproHum #0892-01: The painful route to consistent results: A reproduction study of human evaluation in NLG](https://aclanthology.org/2024.humeval-1.24) (Mondella et al., HumEval-WS 2024)
ACL