@inproceedings{klubicka-kelleher-2024-reprohum,
title = "{R}epro{H}um {\#}1018-09: Reproducing Human Evaluations of Redundancy Errors in Data-To-Text Systems",
author = "Klubi{\v{c}}ka, Filip and
Kelleher, John D.",
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-1.16",
pages = "163--198",
abstract = "This paper describes a reproduction of a human evaluation study evaluating redundancies generated in automatically generated text from a data-to-text system. While the scope of the original study is broader, a human evaluation{---}a manual error analysis{---}is included as part of the system evaluation. We attempt a reproduction of this human evaluation, however while the authors annotate multiple properties of the generated text, we focus exclusively on a single quality criterion, that of redundancy. In focusing our study on a single minimal reproducible experimental unit, with the experiment being fairly straightforward and all data made available by the authors, we encountered no challenges with our reproduction and were able to reproduce the trend found in the original experiment. However, while still confirming the general trend, we found that both our annotators identified twice as many errors in the dataset than the original authors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klubicka-kelleher-2024-reprohum">
<titleInfo>
<title>ReproHum #1018-09: Reproducing Human Evaluations of Redundancy Errors in Data-To-Text Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Klubička</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Kelleher</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 describes a reproduction of a human evaluation study evaluating redundancies generated in automatically generated text from a data-to-text system. While the scope of the original study is broader, a human evaluation—a manual error analysis—is included as part of the system evaluation. We attempt a reproduction of this human evaluation, however while the authors annotate multiple properties of the generated text, we focus exclusively on a single quality criterion, that of redundancy. In focusing our study on a single minimal reproducible experimental unit, with the experiment being fairly straightforward and all data made available by the authors, we encountered no challenges with our reproduction and were able to reproduce the trend found in the original experiment. However, while still confirming the general trend, we found that both our annotators identified twice as many errors in the dataset than the original authors.</abstract>
<identifier type="citekey">klubicka-kelleher-2024-reprohum</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.16</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>163</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproHum #1018-09: Reproducing Human Evaluations of Redundancy Errors in Data-To-Text Systems
%A Klubička, Filip
%A Kelleher, John D.
%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 klubicka-kelleher-2024-reprohum
%X This paper describes a reproduction of a human evaluation study evaluating redundancies generated in automatically generated text from a data-to-text system. While the scope of the original study is broader, a human evaluation—a manual error analysis—is included as part of the system evaluation. We attempt a reproduction of this human evaluation, however while the authors annotate multiple properties of the generated text, we focus exclusively on a single quality criterion, that of redundancy. In focusing our study on a single minimal reproducible experimental unit, with the experiment being fairly straightforward and all data made available by the authors, we encountered no challenges with our reproduction and were able to reproduce the trend found in the original experiment. However, while still confirming the general trend, we found that both our annotators identified twice as many errors in the dataset than the original authors.
%U https://aclanthology.org/2024.humeval-1.16
%P 163-198
Markdown (Informal)
[ReproHum #1018-09: Reproducing Human Evaluations of Redundancy Errors in Data-To-Text Systems](https://aclanthology.org/2024.humeval-1.16) (Klubička & Kelleher, HumEval-WS 2024)
ACL