@inproceedings{van-miltenburg-etal-2024-reprohum,
title = "{R}epro{H}um: {\#}0033-03: How Reproducible Are Fluency Ratings of Generated Text? A Reproduction of {A}ugust et al. 2022",
author = "van Miltenburg, Emiel and
Braggaar, Anouck and
Braun, Nadine and
Goudbeek, Martijn and
Krahmer, Emiel and
van der Lee, Chris and
Pauws, Steffen and
Tomas, Fr{\'e}d{\'e}ric",
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-1.13",
pages = "132--144",
abstract = "In earlier work, August et al. (2022) evaluated three different Natural Language Generation systems on their ability to generate fluent, relevant, and factual scientific definitions. As part of the ReproHum project (Belz et al., 2023), we carried out a partial reproduction study of their human evaluation procedure, focusing on human fluency ratings. Following the standardised ReproHum procedure, our reproduction study follows the original study as closely as possible, with two raters providing 300 ratings each. In addition to this, we carried out a second study where we collected ratings from eight additional raters and analysed the variability of the ratings. We successfully reproduced the inferential statistics from the original study (i.e. the same hypotheses were supported), albeit with a lower inter-annotator agreement. The remainder of our paper shows significant variation between different raters, raising questions about what it really means to reproduce human evaluation studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-miltenburg-etal-2024-reprohum">
<titleInfo>
<title>ReproHum: #0033-03: How Reproducible Are Fluency Ratings of Generated Text? A Reproduction of August et al. 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">van Miltenburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anouck</namePart>
<namePart type="family">Braggaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadine</namePart>
<namePart type="family">Braun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martijn</namePart>
<namePart type="family">Goudbeek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">Krahmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">van der Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Pauws</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Tomas</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 earlier work, August et al. (2022) evaluated three different Natural Language Generation systems on their ability to generate fluent, relevant, and factual scientific definitions. As part of the ReproHum project (Belz et al., 2023), we carried out a partial reproduction study of their human evaluation procedure, focusing on human fluency ratings. Following the standardised ReproHum procedure, our reproduction study follows the original study as closely as possible, with two raters providing 300 ratings each. In addition to this, we carried out a second study where we collected ratings from eight additional raters and analysed the variability of the ratings. We successfully reproduced the inferential statistics from the original study (i.e. the same hypotheses were supported), albeit with a lower inter-annotator agreement. The remainder of our paper shows significant variation between different raters, raising questions about what it really means to reproduce human evaluation studies.</abstract>
<identifier type="citekey">van-miltenburg-etal-2024-reprohum</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.13</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>132</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproHum: #0033-03: How Reproducible Are Fluency Ratings of Generated Text? A Reproduction of August et al. 2022
%A van Miltenburg, Emiel
%A Braggaar, Anouck
%A Braun, Nadine
%A Goudbeek, Martijn
%A Krahmer, Emiel
%A van der Lee, Chris
%A Pauws, Steffen
%A Tomas, Frédéric
%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 van-miltenburg-etal-2024-reprohum
%X In earlier work, August et al. (2022) evaluated three different Natural Language Generation systems on their ability to generate fluent, relevant, and factual scientific definitions. As part of the ReproHum project (Belz et al., 2023), we carried out a partial reproduction study of their human evaluation procedure, focusing on human fluency ratings. Following the standardised ReproHum procedure, our reproduction study follows the original study as closely as possible, with two raters providing 300 ratings each. In addition to this, we carried out a second study where we collected ratings from eight additional raters and analysed the variability of the ratings. We successfully reproduced the inferential statistics from the original study (i.e. the same hypotheses were supported), albeit with a lower inter-annotator agreement. The remainder of our paper shows significant variation between different raters, raising questions about what it really means to reproduce human evaluation studies.
%U https://aclanthology.org/2024.humeval-1.13
%P 132-144
Markdown (Informal)
[ReproHum: #0033-03: How Reproducible Are Fluency Ratings of Generated Text? A Reproduction of August et al. 2022](https://aclanthology.org/2024.humeval-1.13) (van Miltenburg et al., HumEval-WS 2024)
ACL
- Emiel van Miltenburg, Anouck Braggaar, Nadine Braun, Martijn Goudbeek, Emiel Krahmer, Chris van der Lee, Steffen Pauws, and Frédéric Tomas. 2024. ReproHum: #0033-03: How Reproducible Are Fluency Ratings of Generated Text? A Reproduction of August et al. 2022. In Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024, pages 132–144, Torino, Italia. ELRA and ICCL.