@inproceedings{gonzalez-corbelle-etal-2024-reprohum,
title = "{R}epro{H}um {\#}0927-3: Reproducing The Human Evaluation Of The {DE}xperts Controlled Text Generation Method",
author = "Gonz{\'a}lez Corbelle, Javier and
Vivel Couso, Ainhoa and
Alonso-Moral, Jose Maria and
Bugar{\'\i}n-Diz, Alberto",
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-1.15",
pages = "153--162",
abstract = "This paper presents a reproduction study aimed at reproducing and validating a human NLP evaluation performed for the DExperts text generation method. The original study introduces DExperts, a controlled text generation method, evaluated using non-toxic prompts from the RealToxicityPrompts dataset. Our reproduction study aims to reproduce the human evaluation of the continuations generated by DExperts in comparison with four baseline methods, in terms of toxicity, topicality, and fluency. We first describe the agreed approach for reproduction within the ReproHum project and detail the configuration of the original evaluation, including necessary adaptations for reproduction. Then, we make a comparison of our reproduction results with those reported in the reproduced paper. Interestingly, we observe how the human evaluators in our experiment appreciate higher quality in the texts generated by DExperts in terms of less toxicity and better fluency. All in all, new scores are higher, also for the baseline methods. This study contributes to ongoing efforts in ensuring the reproducibility and reliability of findings in NLP evaluation and emphasizes the critical role of robust methodologies in advancing the field.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-corbelle-etal-2024-reprohum">
<titleInfo>
<title>ReproHum #0927-3: Reproducing The Human Evaluation Of The DExperts Controlled Text Generation Method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">González Corbelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ainhoa</namePart>
<namePart type="family">Vivel Couso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Alonso-Moral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Bugarín-Diz</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 a reproduction study aimed at reproducing and validating a human NLP evaluation performed for the DExperts text generation method. The original study introduces DExperts, a controlled text generation method, evaluated using non-toxic prompts from the RealToxicityPrompts dataset. Our reproduction study aims to reproduce the human evaluation of the continuations generated by DExperts in comparison with four baseline methods, in terms of toxicity, topicality, and fluency. We first describe the agreed approach for reproduction within the ReproHum project and detail the configuration of the original evaluation, including necessary adaptations for reproduction. Then, we make a comparison of our reproduction results with those reported in the reproduced paper. Interestingly, we observe how the human evaluators in our experiment appreciate higher quality in the texts generated by DExperts in terms of less toxicity and better fluency. All in all, new scores are higher, also for the baseline methods. This study contributes to ongoing efforts in ensuring the reproducibility and reliability of findings in NLP evaluation and emphasizes the critical role of robust methodologies in advancing the field.</abstract>
<identifier type="citekey">gonzalez-corbelle-etal-2024-reprohum</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.15</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>153</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproHum #0927-3: Reproducing The Human Evaluation Of The DExperts Controlled Text Generation Method
%A González Corbelle, Javier
%A Vivel Couso, Ainhoa
%A Alonso-Moral, Jose Maria
%A Bugarín-Diz, Alberto
%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 gonzalez-corbelle-etal-2024-reprohum
%X This paper presents a reproduction study aimed at reproducing and validating a human NLP evaluation performed for the DExperts text generation method. The original study introduces DExperts, a controlled text generation method, evaluated using non-toxic prompts from the RealToxicityPrompts dataset. Our reproduction study aims to reproduce the human evaluation of the continuations generated by DExperts in comparison with four baseline methods, in terms of toxicity, topicality, and fluency. We first describe the agreed approach for reproduction within the ReproHum project and detail the configuration of the original evaluation, including necessary adaptations for reproduction. Then, we make a comparison of our reproduction results with those reported in the reproduced paper. Interestingly, we observe how the human evaluators in our experiment appreciate higher quality in the texts generated by DExperts in terms of less toxicity and better fluency. All in all, new scores are higher, also for the baseline methods. This study contributes to ongoing efforts in ensuring the reproducibility and reliability of findings in NLP evaluation and emphasizes the critical role of robust methodologies in advancing the field.
%U https://aclanthology.org/2024.humeval-1.15
%P 153-162
Markdown (Informal)
[ReproHum #0927-3: Reproducing The Human Evaluation Of The DExperts Controlled Text Generation Method](https://aclanthology.org/2024.humeval-1.15) (González Corbelle et al., HumEval-WS 2024)
ACL