@inproceedings{hegde-etal-2021-mum,
title = "{MUM} at {C}om{MA}@{ICON}: Multilingual Gender Biased and Communal Language Identification Using Supervised Learning Approaches",
author = "Hegde, Asha and
Anusha, Mudoor Devadas and
Coelho, Sharal and
Shashirekha, Hosahalli Lakshmaiah",
editor = "Kumar, Ritesh and
Singh, Siddharth and
Nandi, Enakshi and
Ratan, Shyam and
Devi, Laishram Niranjana and
Lahiri, Bornini and
Bansal, Akanksha and
Bhagat, Akash and
Dawer, Yogesh",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing: Shared Task on Multilingual Gender Biased and Communal Language Identification",
month = dec,
year = "2021",
address = "NIT Silchar",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-multigen.10",
pages = "64--69",
abstract = "Due to the rapid rise of social networks and micro-blogging websites, communication between people from different religion, caste, creed, cultural and psychological backgrounds has become more direct leading to the increase in cyber conflicts between people. This in turn has given rise to more and more hate speech and usage of abusive words to the point that it has become a serious problem creating negative impacts on the society. As a result, it is imperative to identify and filter such content on social media to prevent its further spread and the damage it is going to cause. Further, filtering such huge data requires automated tools since doing it manually is labor intensive and error prone. Added to this is the complex code-mixed and multi-scripted nature of social media text. To address the challenges of abusive content detection on social media, in this paper, we, team MUM, propose Machine Learning (ML) and Deep Learning (DL) models submitted to Multilingual Gender Biased and Communal Language Identification (ComMA@ICON) shared task at International Conference on Natural Language Processing (ICON) 2021. Word uni-grams, char n-grams, and emoji vectors are combined as features to train a ML Elastic-net regression model and multi-lingual Bidirectional Encoder Representations from Transformers (mBERT) is fine-tuned for a DL model. Out of the two, fine-tuned mBERT model performed better with an instance-F1 score of 0.326, 0.390, 0.343, 0.359 for Meitei, Bangla, Hindi, Multilingual texts respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hegde-etal-2021-mum">
<titleInfo>
<title>MUM at ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Using Supervised Learning Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asha</namePart>
<namePart type="family">Hegde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mudoor</namePart>
<namePart type="given">Devadas</namePart>
<namePart type="family">Anusha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharal</namePart>
<namePart type="family">Coelho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosahalli</namePart>
<namePart type="given">Lakshmaiah</namePart>
<namePart type="family">Shashirekha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing: Shared Task on Multilingual Gender Biased and Communal Language Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enakshi</namePart>
<namePart type="family">Nandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laishram</namePart>
<namePart type="given">Niranjana</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bornini</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akanksha</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Bhagat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yogesh</namePart>
<namePart type="family">Dawer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">NIT Silchar</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to the rapid rise of social networks and micro-blogging websites, communication between people from different religion, caste, creed, cultural and psychological backgrounds has become more direct leading to the increase in cyber conflicts between people. This in turn has given rise to more and more hate speech and usage of abusive words to the point that it has become a serious problem creating negative impacts on the society. As a result, it is imperative to identify and filter such content on social media to prevent its further spread and the damage it is going to cause. Further, filtering such huge data requires automated tools since doing it manually is labor intensive and error prone. Added to this is the complex code-mixed and multi-scripted nature of social media text. To address the challenges of abusive content detection on social media, in this paper, we, team MUM, propose Machine Learning (ML) and Deep Learning (DL) models submitted to Multilingual Gender Biased and Communal Language Identification (ComMA@ICON) shared task at International Conference on Natural Language Processing (ICON) 2021. Word uni-grams, char n-grams, and emoji vectors are combined as features to train a ML Elastic-net regression model and multi-lingual Bidirectional Encoder Representations from Transformers (mBERT) is fine-tuned for a DL model. Out of the two, fine-tuned mBERT model performed better with an instance-F1 score of 0.326, 0.390, 0.343, 0.359 for Meitei, Bangla, Hindi, Multilingual texts respectively.</abstract>
<identifier type="citekey">hegde-etal-2021-mum</identifier>
<location>
<url>https://aclanthology.org/2021.icon-multigen.10</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>64</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MUM at ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Using Supervised Learning Approaches
%A Hegde, Asha
%A Anusha, Mudoor Devadas
%A Coelho, Sharal
%A Shashirekha, Hosahalli Lakshmaiah
%Y Kumar, Ritesh
%Y Singh, Siddharth
%Y Nandi, Enakshi
%Y Ratan, Shyam
%Y Devi, Laishram Niranjana
%Y Lahiri, Bornini
%Y Bansal, Akanksha
%Y Bhagat, Akash
%Y Dawer, Yogesh
%S Proceedings of the 18th International Conference on Natural Language Processing: Shared Task on Multilingual Gender Biased and Communal Language Identification
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C NIT Silchar
%F hegde-etal-2021-mum
%X Due to the rapid rise of social networks and micro-blogging websites, communication between people from different religion, caste, creed, cultural and psychological backgrounds has become more direct leading to the increase in cyber conflicts between people. This in turn has given rise to more and more hate speech and usage of abusive words to the point that it has become a serious problem creating negative impacts on the society. As a result, it is imperative to identify and filter such content on social media to prevent its further spread and the damage it is going to cause. Further, filtering such huge data requires automated tools since doing it manually is labor intensive and error prone. Added to this is the complex code-mixed and multi-scripted nature of social media text. To address the challenges of abusive content detection on social media, in this paper, we, team MUM, propose Machine Learning (ML) and Deep Learning (DL) models submitted to Multilingual Gender Biased and Communal Language Identification (ComMA@ICON) shared task at International Conference on Natural Language Processing (ICON) 2021. Word uni-grams, char n-grams, and emoji vectors are combined as features to train a ML Elastic-net regression model and multi-lingual Bidirectional Encoder Representations from Transformers (mBERT) is fine-tuned for a DL model. Out of the two, fine-tuned mBERT model performed better with an instance-F1 score of 0.326, 0.390, 0.343, 0.359 for Meitei, Bangla, Hindi, Multilingual texts respectively.
%U https://aclanthology.org/2021.icon-multigen.10
%P 64-69
Markdown (Informal)
[MUM at ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Using Supervised Learning Approaches](https://aclanthology.org/2021.icon-multigen.10) (Hegde et al., ICON 2021)
ACL