@inproceedings{singh-thakur-2024-generalizable,
title = "Generalizable Multilingual Hate Speech Detection on Low Resource {I}ndian Languages using Fair Selection in Federated Learning",
author = "Singh, Akshay and
Thakur, Rahul",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.400",
doi = "10.18653/v1/2024.naacl-long.400",
pages = "7211--7221",
abstract = "Social media, originally meant for peaceful communication, now faces issues with hate speech. Detecting hate speech from social media in Indian languages with linguistic diversity and cultural nuances presents a complex and challenging task. Furthermore, traditional methods involve sharing of users{'} sensitive data with a server for model training making it undesirable and involving potential risk to their privacy remained under-studied. In this paper, we combined various low-resource language datasets and propose MultiFED, a federated approach that performs effectively to detect hate speech. MultiFED utilizes continuous adaptation and fine-tuning to aid generalization using subsets of multilingual data overcoming the limitations of data scarcity. Extensive experiments are conducted on 13 Indic datasets across five different pre-trained models. The results show that MultiFED outperforms the state-of-the-art baselines by 8{\%} (approx.) in terms of Accuracy and by 12{\%} (approx.) in terms of F-Score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-thakur-2024-generalizable">
<titleInfo>
<title>Generalizable Multilingual Hate Speech Detection on Low Resource Indian Languages using Fair Selection in Federated Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshay</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Thakur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media, originally meant for peaceful communication, now faces issues with hate speech. Detecting hate speech from social media in Indian languages with linguistic diversity and cultural nuances presents a complex and challenging task. Furthermore, traditional methods involve sharing of users’ sensitive data with a server for model training making it undesirable and involving potential risk to their privacy remained under-studied. In this paper, we combined various low-resource language datasets and propose MultiFED, a federated approach that performs effectively to detect hate speech. MultiFED utilizes continuous adaptation and fine-tuning to aid generalization using subsets of multilingual data overcoming the limitations of data scarcity. Extensive experiments are conducted on 13 Indic datasets across five different pre-trained models. The results show that MultiFED outperforms the state-of-the-art baselines by 8% (approx.) in terms of Accuracy and by 12% (approx.) in terms of F-Score.</abstract>
<identifier type="citekey">singh-thakur-2024-generalizable</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.400</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.400</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7211</start>
<end>7221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizable Multilingual Hate Speech Detection on Low Resource Indian Languages using Fair Selection in Federated Learning
%A Singh, Akshay
%A Thakur, Rahul
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F singh-thakur-2024-generalizable
%X Social media, originally meant for peaceful communication, now faces issues with hate speech. Detecting hate speech from social media in Indian languages with linguistic diversity and cultural nuances presents a complex and challenging task. Furthermore, traditional methods involve sharing of users’ sensitive data with a server for model training making it undesirable and involving potential risk to their privacy remained under-studied. In this paper, we combined various low-resource language datasets and propose MultiFED, a federated approach that performs effectively to detect hate speech. MultiFED utilizes continuous adaptation and fine-tuning to aid generalization using subsets of multilingual data overcoming the limitations of data scarcity. Extensive experiments are conducted on 13 Indic datasets across five different pre-trained models. The results show that MultiFED outperforms the state-of-the-art baselines by 8% (approx.) in terms of Accuracy and by 12% (approx.) in terms of F-Score.
%R 10.18653/v1/2024.naacl-long.400
%U https://aclanthology.org/2024.naacl-long.400
%U https://doi.org/10.18653/v1/2024.naacl-long.400
%P 7211-7221
Markdown (Informal)
[Generalizable Multilingual Hate Speech Detection on Low Resource Indian Languages using Fair Selection in Federated Learning](https://aclanthology.org/2024.naacl-long.400) (Singh & Thakur, NAACL 2024)
ACL