@inproceedings{sasidharan-nair-etal-2024-exploring,
title = "Exploring Reproducibility of Human-Labelled Data for Code-Mixed Sentiment Analysis",
author = "Sasidharan Nair, Sachin and
Dinkar, Tanvi and
Abercrombie, Gavin",
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-1.11",
pages = "114--124",
abstract = "Growing awareness of a {`}Reproducibility Crisis{'} in natural language processing (NLP) has focused on human evaluations of generative systems. While labelling for supervised classification tasks makes up a large part of human input to systems, the reproduction of such efforts has thus far not been been explored. In this paper, we re-implement a human data collection study for sentiment analysis of code-mixed Malayalam movie reviews, as well as automated classification experiments. We find that missing and under-specified information makes reproduction challenging, and we observe potentially consequential differences between the original labels and those we collect. Classification results indicate that the reliability of the labels is important for stable performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sasidharan-nair-etal-2024-exploring">
<titleInfo>
<title>Exploring Reproducibility of Human-Labelled Data for Code-Mixed Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Sasidharan Nair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanvi</namePart>
<namePart type="family">Dinkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gavin</namePart>
<namePart type="family">Abercrombie</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>Growing awareness of a ‘Reproducibility Crisis’ in natural language processing (NLP) has focused on human evaluations of generative systems. While labelling for supervised classification tasks makes up a large part of human input to systems, the reproduction of such efforts has thus far not been been explored. In this paper, we re-implement a human data collection study for sentiment analysis of code-mixed Malayalam movie reviews, as well as automated classification experiments. We find that missing and under-specified information makes reproduction challenging, and we observe potentially consequential differences between the original labels and those we collect. Classification results indicate that the reliability of the labels is important for stable performance.</abstract>
<identifier type="citekey">sasidharan-nair-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.11</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>114</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Reproducibility of Human-Labelled Data for Code-Mixed Sentiment Analysis
%A Sasidharan Nair, Sachin
%A Dinkar, Tanvi
%A Abercrombie, Gavin
%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 sasidharan-nair-etal-2024-exploring
%X Growing awareness of a ‘Reproducibility Crisis’ in natural language processing (NLP) has focused on human evaluations of generative systems. While labelling for supervised classification tasks makes up a large part of human input to systems, the reproduction of such efforts has thus far not been been explored. In this paper, we re-implement a human data collection study for sentiment analysis of code-mixed Malayalam movie reviews, as well as automated classification experiments. We find that missing and under-specified information makes reproduction challenging, and we observe potentially consequential differences between the original labels and those we collect. Classification results indicate that the reliability of the labels is important for stable performance.
%U https://aclanthology.org/2024.humeval-1.11
%P 114-124
Markdown (Informal)
[Exploring Reproducibility of Human-Labelled Data for Code-Mixed Sentiment Analysis](https://aclanthology.org/2024.humeval-1.11) (Sasidharan Nair et al., HumEval-WS 2024)
ACL