@inproceedings{marchiori-manerba-etal-2022-bias,
title = "Bias Discovery within Human Raters: A Case Study of the Jigsaw Dataset",
author = "Marchiori Manerba, Marta and
Guidotti, Riccardo and
Passaro, Lucia and
Ruggieri, Salvatore",
editor = "Abercrombie, Gavin and
Basile, Valerio and
Tonelli, Sara and
Rieser, Verena and
Uma, Alexandra",
booktitle = "Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.nlperspectives-1.4",
pages = "26--31",
abstract = "Understanding and quantifying the bias introduced by human annotation of data is a crucial problem for trustworthy supervised learning. Recently, a perspectivist trend has emerged in the NLP community, focusing on the inadequacy of previous aggregation schemes, which suppose the existence of single ground truth. This assumption is particularly problematic for sensitive tasks involving subjective human judgments, such as toxicity detection. To address these issues, we propose a preliminary approach for bias discovery within human raters by exploring individual ratings for specific sensitive topics annotated in the texts. Our analysis{'}s object consists of the Jigsaw dataset, a collection of comments aiming at challenging online toxicity identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marchiori-manerba-etal-2022-bias">
<titleInfo>
<title>Bias Discovery within Human Raters: A Case Study of the Jigsaw Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Marchiori Manerba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riccardo</namePart>
<namePart type="family">Guidotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Passaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salvatore</namePart>
<namePart type="family">Ruggieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gavin</namePart>
<namePart type="family">Abercrombie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Tonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Rieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Uma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding and quantifying the bias introduced by human annotation of data is a crucial problem for trustworthy supervised learning. Recently, a perspectivist trend has emerged in the NLP community, focusing on the inadequacy of previous aggregation schemes, which suppose the existence of single ground truth. This assumption is particularly problematic for sensitive tasks involving subjective human judgments, such as toxicity detection. To address these issues, we propose a preliminary approach for bias discovery within human raters by exploring individual ratings for specific sensitive topics annotated in the texts. Our analysis’s object consists of the Jigsaw dataset, a collection of comments aiming at challenging online toxicity identification.</abstract>
<identifier type="citekey">marchiori-manerba-etal-2022-bias</identifier>
<location>
<url>https://aclanthology.org/2022.nlperspectives-1.4</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>26</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bias Discovery within Human Raters: A Case Study of the Jigsaw Dataset
%A Marchiori Manerba, Marta
%A Guidotti, Riccardo
%A Passaro, Lucia
%A Ruggieri, Salvatore
%Y Abercrombie, Gavin
%Y Basile, Valerio
%Y Tonelli, Sara
%Y Rieser, Verena
%Y Uma, Alexandra
%S Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F marchiori-manerba-etal-2022-bias
%X Understanding and quantifying the bias introduced by human annotation of data is a crucial problem for trustworthy supervised learning. Recently, a perspectivist trend has emerged in the NLP community, focusing on the inadequacy of previous aggregation schemes, which suppose the existence of single ground truth. This assumption is particularly problematic for sensitive tasks involving subjective human judgments, such as toxicity detection. To address these issues, we propose a preliminary approach for bias discovery within human raters by exploring individual ratings for specific sensitive topics annotated in the texts. Our analysis’s object consists of the Jigsaw dataset, a collection of comments aiming at challenging online toxicity identification.
%U https://aclanthology.org/2022.nlperspectives-1.4
%P 26-31
Markdown (Informal)
[Bias Discovery within Human Raters: A Case Study of the Jigsaw Dataset](https://aclanthology.org/2022.nlperspectives-1.4) (Marchiori Manerba et al., NLPerspectives 2022)
ACL