@inproceedings{rizwan-etal-2020-hate,
title = "Hate-Speech and Offensive Language Detection in {R}oman {U}rdu",
author = "Rizwan, Hammad and
Shakeel, Muhammad Haroon and
Karim, Asim",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.197",
doi = "10.18653/v1/2020.emnlp-main.197",
pages = "2512--2522",
abstract = "The task of automatic hate-speech and offensive language detection in social media content is of utmost importance due to its implications in unprejudiced society concerning race, gender, or religion. Existing research in this area, however, is mainly focused on the English language, limiting the applicability to particular demographics. Despite its prevalence, Roman Urdu (RU) lacks language resources, annotated datasets, and language models for this task. In this study, we: (1) Present a lexicon of hateful words in RU, (2) Develop an annotated dataset called RUHSOLD consisting of 10,012 tweets in RU with both coarse-grained and fine-grained labels of hate-speech and offensive language, (3) Explore the feasibility of transfer learning of five existing embedding models to RU, (4) Propose a novel deep learning architecture called CNN-gram for hate-speech and offensive language detection and compare its performance with seven current baseline approaches on RUHSOLD dataset, and (5) Train domain-specific embeddings on more than 4.7 million tweets and make them publicly available. We conclude that transfer learning is more beneficial as compared to training embedding from scratch and that the proposed model exhibits greater robustness as compared to the baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rizwan-etal-2020-hate">
<titleInfo>
<title>Hate-Speech and Offensive Language Detection in Roman Urdu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hammad</namePart>
<namePart type="family">Rizwan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Haroon</namePart>
<namePart type="family">Shakeel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asim</namePart>
<namePart type="family">Karim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of automatic hate-speech and offensive language detection in social media content is of utmost importance due to its implications in unprejudiced society concerning race, gender, or religion. Existing research in this area, however, is mainly focused on the English language, limiting the applicability to particular demographics. Despite its prevalence, Roman Urdu (RU) lacks language resources, annotated datasets, and language models for this task. In this study, we: (1) Present a lexicon of hateful words in RU, (2) Develop an annotated dataset called RUHSOLD consisting of 10,012 tweets in RU with both coarse-grained and fine-grained labels of hate-speech and offensive language, (3) Explore the feasibility of transfer learning of five existing embedding models to RU, (4) Propose a novel deep learning architecture called CNN-gram for hate-speech and offensive language detection and compare its performance with seven current baseline approaches on RUHSOLD dataset, and (5) Train domain-specific embeddings on more than 4.7 million tweets and make them publicly available. We conclude that transfer learning is more beneficial as compared to training embedding from scratch and that the proposed model exhibits greater robustness as compared to the baselines.</abstract>
<identifier type="citekey">rizwan-etal-2020-hate</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.197</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.197</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2512</start>
<end>2522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hate-Speech and Offensive Language Detection in Roman Urdu
%A Rizwan, Hammad
%A Shakeel, Muhammad Haroon
%A Karim, Asim
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F rizwan-etal-2020-hate
%X The task of automatic hate-speech and offensive language detection in social media content is of utmost importance due to its implications in unprejudiced society concerning race, gender, or religion. Existing research in this area, however, is mainly focused on the English language, limiting the applicability to particular demographics. Despite its prevalence, Roman Urdu (RU) lacks language resources, annotated datasets, and language models for this task. In this study, we: (1) Present a lexicon of hateful words in RU, (2) Develop an annotated dataset called RUHSOLD consisting of 10,012 tweets in RU with both coarse-grained and fine-grained labels of hate-speech and offensive language, (3) Explore the feasibility of transfer learning of five existing embedding models to RU, (4) Propose a novel deep learning architecture called CNN-gram for hate-speech and offensive language detection and compare its performance with seven current baseline approaches on RUHSOLD dataset, and (5) Train domain-specific embeddings on more than 4.7 million tweets and make them publicly available. We conclude that transfer learning is more beneficial as compared to training embedding from scratch and that the proposed model exhibits greater robustness as compared to the baselines.
%R 10.18653/v1/2020.emnlp-main.197
%U https://aclanthology.org/2020.emnlp-main.197
%U https://doi.org/10.18653/v1/2020.emnlp-main.197
%P 2512-2522
Markdown (Informal)
[Hate-Speech and Offensive Language Detection in Roman Urdu](https://aclanthology.org/2020.emnlp-main.197) (Rizwan et al., EMNLP 2020)
ACL