@inproceedings{bhandari-goyal-2022-bitsa,
title = "bitsa{\_}nlp@{LT}-{EDI}-{ACL}2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media Comments",
author = "Bhandari, Vitthal and
Goyal, Poonam",
editor = "Chakravarthi, Bharathi Raja and
Bharathi, B and
McCrae, John P and
Zarrouk, Manel and
Bali, Kalika and
Buitelaar, Paul",
booktitle = "Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ltedi-1.18",
doi = "10.18653/v1/2022.ltedi-1.18",
pages = "149--154",
abstract = "Online social networks are ubiquitous and user-friendly. Nevertheless, it is vital to detect and moderate offensive content to maintain decency and empathy. However, mining social media texts is a complex task since users don{'}t adhere to any fixed patterns. Comments can be written in any combination of languages and many of them may be low-resource. In this paper, we present our system for the LT-EDI shared task on detecting homophobia and transphobia in social media comments. We experiment with a number of monolingual and multilingual transformer based models such as mBERT along with a data augmentation technique for tackling class imbalance. Such pretrained large models have recently shown tremendous success on a variety of benchmark tasks in natural language processing. We observe their performance on a carefully annotated, real life dataset of YouTube comments in English as well as Tamil. Our submission achieved ranks 9, 6 and 3 with a macro-averaged F1-score of 0.42, 0.64 and 0.58 in the English, Tamil and Tamil-English subtasks respectively. The code for the system has been open sourced.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhandari-goyal-2022-bitsa">
<titleInfo>
<title>bitsa_nlp@LT-EDI-ACL2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vitthal</namePart>
<namePart type="family">Bhandari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Poonam</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Bharathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manel</namePart>
<namePart type="family">Zarrouk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Online social networks are ubiquitous and user-friendly. Nevertheless, it is vital to detect and moderate offensive content to maintain decency and empathy. However, mining social media texts is a complex task since users don’t adhere to any fixed patterns. Comments can be written in any combination of languages and many of them may be low-resource. In this paper, we present our system for the LT-EDI shared task on detecting homophobia and transphobia in social media comments. We experiment with a number of monolingual and multilingual transformer based models such as mBERT along with a data augmentation technique for tackling class imbalance. Such pretrained large models have recently shown tremendous success on a variety of benchmark tasks in natural language processing. We observe their performance on a carefully annotated, real life dataset of YouTube comments in English as well as Tamil. Our submission achieved ranks 9, 6 and 3 with a macro-averaged F1-score of 0.42, 0.64 and 0.58 in the English, Tamil and Tamil-English subtasks respectively. The code for the system has been open sourced.</abstract>
<identifier type="citekey">bhandari-goyal-2022-bitsa</identifier>
<identifier type="doi">10.18653/v1/2022.ltedi-1.18</identifier>
<location>
<url>https://aclanthology.org/2022.ltedi-1.18</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>149</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T bitsa_nlp@LT-EDI-ACL2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media Comments
%A Bhandari, Vitthal
%A Goyal, Poonam
%Y Chakravarthi, Bharathi Raja
%Y Bharathi, B.
%Y McCrae, John P.
%Y Zarrouk, Manel
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F bhandari-goyal-2022-bitsa
%X Online social networks are ubiquitous and user-friendly. Nevertheless, it is vital to detect and moderate offensive content to maintain decency and empathy. However, mining social media texts is a complex task since users don’t adhere to any fixed patterns. Comments can be written in any combination of languages and many of them may be low-resource. In this paper, we present our system for the LT-EDI shared task on detecting homophobia and transphobia in social media comments. We experiment with a number of monolingual and multilingual transformer based models such as mBERT along with a data augmentation technique for tackling class imbalance. Such pretrained large models have recently shown tremendous success on a variety of benchmark tasks in natural language processing. We observe their performance on a carefully annotated, real life dataset of YouTube comments in English as well as Tamil. Our submission achieved ranks 9, 6 and 3 with a macro-averaged F1-score of 0.42, 0.64 and 0.58 in the English, Tamil and Tamil-English subtasks respectively. The code for the system has been open sourced.
%R 10.18653/v1/2022.ltedi-1.18
%U https://aclanthology.org/2022.ltedi-1.18
%U https://doi.org/10.18653/v1/2022.ltedi-1.18
%P 149-154
Markdown (Informal)
[bitsa_nlp@LT-EDI-ACL2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media Comments](https://aclanthology.org/2022.ltedi-1.18) (Bhandari & Goyal, LTEDI 2022)
ACL