@inproceedings{lango-etal-2024-reprohum,
title = "{R}epro{H}um {\#}0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility",
author = "Lango, Mateusz and
Schmidtova, Patricia and
Balloccu, Simone and
Dusek, Ondrej",
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-1.20",
pages = "229--237",
abstract = "In this paper, we describe several reproductions of a human evaluation experiment measuring the quality of automatic dialogue summarization (Feng et al., 2021). We investigate the impact of the annotators{'} highest level of education, field of study, and native language on the evaluation of the informativeness of the summary. We find that the evaluation is relatively consistent regardless of these factors, but the biggest impact seems to be a prior specific background in natural language processing (as opposed to, e.g. a background in computer sci- ence). We also find that the experiment setup (asking for single vs. multiple criteria) may have an impact on the results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lango-etal-2024-reprohum">
<titleInfo>
<title>ReproHum #0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Lango</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Schmidtova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</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 this paper, we describe several reproductions of a human evaluation experiment measuring the quality of automatic dialogue summarization (Feng et al., 2021). We investigate the impact of the annotators’ highest level of education, field of study, and native language on the evaluation of the informativeness of the summary. We find that the evaluation is relatively consistent regardless of these factors, but the biggest impact seems to be a prior specific background in natural language processing (as opposed to, e.g. a background in computer sci- ence). We also find that the experiment setup (asking for single vs. multiple criteria) may have an impact on the results.</abstract>
<identifier type="citekey">lango-etal-2024-reprohum</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.20</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>229</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproHum #0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility
%A Lango, Mateusz
%A Schmidtova, Patricia
%A Balloccu, Simone
%A Dusek, Ondrej
%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 lango-etal-2024-reprohum
%X In this paper, we describe several reproductions of a human evaluation experiment measuring the quality of automatic dialogue summarization (Feng et al., 2021). We investigate the impact of the annotators’ highest level of education, field of study, and native language on the evaluation of the informativeness of the summary. We find that the evaluation is relatively consistent regardless of these factors, but the biggest impact seems to be a prior specific background in natural language processing (as opposed to, e.g. a background in computer sci- ence). We also find that the experiment setup (asking for single vs. multiple criteria) may have an impact on the results.
%U https://aclanthology.org/2024.humeval-1.20
%P 229-237
Markdown (Informal)
[ReproHum #0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility](https://aclanthology.org/2024.humeval-1.20) (Lango et al., HumEval-WS 2024)
ACL