@inproceedings{cimitan-etal-2024-curation-benchmark,
title = "Curation of Benchmark Templates for Measuring Gender Bias in Named Entity Recognition Models",
author = "Cimitan, Ana and
Alves Pinto, Ana and
Geierhos, Michaela",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.378",
pages = "4238--4246",
abstract = "Named Entity Recognition (NER) constitutes a popular machine learning technique that empowers several natural language processing applications. As with other machine learning applications, NER models have been shown to be susceptible to gender bias. The latter is often assessed using benchmark datasets, which in turn are curated specifically for a given Natural Language Processing (NLP) task. In this work, we investigate the robustness of benchmark templates to detect gender bias and propose a novel method to improve the curation of such datasets. The method, based on masked token prediction, aims to filter out benchmark templates with a higher probability of detecting gender bias in NER models. We tested the method for English and German, using the corresponding fine-tuned BERT base model (cased) as the NER model. The gender gaps detected with templates classified as appropriate by the method were statistically larger than those detected with inappropriate templates. The results were similar for both languages and support the use of the proposed method in the curation of templates designed to detect gender bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cimitan-etal-2024-curation-benchmark">
<titleInfo>
<title>Curation of Benchmark Templates for Measuring Gender Bias in Named Entity Recognition Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Cimitan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Alves Pinto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michaela</namePart>
<namePart type="family">Geierhos</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>Named Entity Recognition (NER) constitutes a popular machine learning technique that empowers several natural language processing applications. As with other machine learning applications, NER models have been shown to be susceptible to gender bias. The latter is often assessed using benchmark datasets, which in turn are curated specifically for a given Natural Language Processing (NLP) task. In this work, we investigate the robustness of benchmark templates to detect gender bias and propose a novel method to improve the curation of such datasets. The method, based on masked token prediction, aims to filter out benchmark templates with a higher probability of detecting gender bias in NER models. We tested the method for English and German, using the corresponding fine-tuned BERT base model (cased) as the NER model. The gender gaps detected with templates classified as appropriate by the method were statistically larger than those detected with inappropriate templates. The results were similar for both languages and support the use of the proposed method in the curation of templates designed to detect gender bias.</abstract>
<identifier type="citekey">cimitan-etal-2024-curation-benchmark</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.378</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4238</start>
<end>4246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Curation of Benchmark Templates for Measuring Gender Bias in Named Entity Recognition Models
%A Cimitan, Ana
%A Alves Pinto, Ana
%A Geierhos, Michaela
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F cimitan-etal-2024-curation-benchmark
%X Named Entity Recognition (NER) constitutes a popular machine learning technique that empowers several natural language processing applications. As with other machine learning applications, NER models have been shown to be susceptible to gender bias. The latter is often assessed using benchmark datasets, which in turn are curated specifically for a given Natural Language Processing (NLP) task. In this work, we investigate the robustness of benchmark templates to detect gender bias and propose a novel method to improve the curation of such datasets. The method, based on masked token prediction, aims to filter out benchmark templates with a higher probability of detecting gender bias in NER models. We tested the method for English and German, using the corresponding fine-tuned BERT base model (cased) as the NER model. The gender gaps detected with templates classified as appropriate by the method were statistically larger than those detected with inappropriate templates. The results were similar for both languages and support the use of the proposed method in the curation of templates designed to detect gender bias.
%U https://aclanthology.org/2024.lrec-main.378
%P 4238-4246
Markdown (Informal)
[Curation of Benchmark Templates for Measuring Gender Bias in Named Entity Recognition Models](https://aclanthology.org/2024.lrec-main.378) (Cimitan et al., LREC-COLING 2024)
ACL