@inproceedings{florescu-etal-2024-upon,
title = "Once Upon a Replication: It is Humans' Turn to Evaluate {AI}`s Understanding of Children`s Stories for {QA} Generation",
author = "Florescu, Andra-Maria and
Micluta-Campeanu, Marius and
Dinu, Liviu P.",
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-1.10/",
pages = "106--113",
abstract = "The following paper presents the outcomes of a collaborative experiment on human evaluation from the ReproNLP 2024 shared task, track B, part of the ReproHum project. For this paper, we evaluated a QAG (question-answer generation) system centered on English children`s storybooks that was presented in a previous research, by using human evaluators for the study. The system generated relevant QA (Question-Answer) pairs based on a dataset with storybooks for early education (kindergarten up to middle school) called FairytaleQA. In the framework of the ReproHum project, we first outline the previous paper and the reproduction strategy that has been decided upon. The complete setup of the first human evaluation is then described, along with the modifications required to replicate it. We also add other relevant related works on this subject. In conclusion, we juxtapose the replication outcomes with those documented in the cited publication. Additionally, we explore the general features of this endeavor as well as its shortcomings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="florescu-etal-2024-upon">
<titleInfo>
<title>Once Upon a Replication: It is Humans’ Turn to Evaluate AI‘s Understanding of Children‘s Stories for QA Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andra-Maria</namePart>
<namePart type="family">Florescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Micluta-Campeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liviu</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dinu</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>The following paper presents the outcomes of a collaborative experiment on human evaluation from the ReproNLP 2024 shared task, track B, part of the ReproHum project. For this paper, we evaluated a QAG (question-answer generation) system centered on English children‘s storybooks that was presented in a previous research, by using human evaluators for the study. The system generated relevant QA (Question-Answer) pairs based on a dataset with storybooks for early education (kindergarten up to middle school) called FairytaleQA. In the framework of the ReproHum project, we first outline the previous paper and the reproduction strategy that has been decided upon. The complete setup of the first human evaluation is then described, along with the modifications required to replicate it. We also add other relevant related works on this subject. In conclusion, we juxtapose the replication outcomes with those documented in the cited publication. Additionally, we explore the general features of this endeavor as well as its shortcomings.</abstract>
<identifier type="citekey">florescu-etal-2024-upon</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.10/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>106</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Once Upon a Replication: It is Humans’ Turn to Evaluate AI‘s Understanding of Children‘s Stories for QA Generation
%A Florescu, Andra-Maria
%A Micluta-Campeanu, Marius
%A Dinu, Liviu P.
%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 florescu-etal-2024-upon
%X The following paper presents the outcomes of a collaborative experiment on human evaluation from the ReproNLP 2024 shared task, track B, part of the ReproHum project. For this paper, we evaluated a QAG (question-answer generation) system centered on English children‘s storybooks that was presented in a previous research, by using human evaluators for the study. The system generated relevant QA (Question-Answer) pairs based on a dataset with storybooks for early education (kindergarten up to middle school) called FairytaleQA. In the framework of the ReproHum project, we first outline the previous paper and the reproduction strategy that has been decided upon. The complete setup of the first human evaluation is then described, along with the modifications required to replicate it. We also add other relevant related works on this subject. In conclusion, we juxtapose the replication outcomes with those documented in the cited publication. Additionally, we explore the general features of this endeavor as well as its shortcomings.
%U https://aclanthology.org/2024.humeval-1.10/
%P 106-113
Markdown (Informal)
[Once Upon a Replication: It is Humans’ Turn to Evaluate AI’s Understanding of Children’s Stories for QA Generation](https://aclanthology.org/2024.humeval-1.10/) (Florescu et al., HumEval 2024)
ACL