@inproceedings{mathur-etal-2018-offend,
title = "Did you offend me? Classification of Offensive Tweets in {H}inglish Language",
author = "Mathur, Puneet and
Sawhney, Ramit and
Ayyar, Meghna and
Shah, Rajiv",
editor = "Fi{\v{s}}er, Darja and
Huang, Ruihong and
Prabhakaran, Vinodkumar and
Voigt, Rob and
Waseem, Zeerak and
Wernimont, Jacqueline",
booktitle = "Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5118",
doi = "10.18653/v1/W18-5118",
pages = "138--148",
abstract = "The use of code-switched languages (\textit{e.g.}, Hinglish, which is derived by the blending of Hindi with the English language) is getting much popular on Twitter due to their ease of communication in native languages. However, spelling variations and absence of grammar rules introduce ambiguity and make it difficult to understand the text automatically. This paper presents the Multi-Input Multi-Channel Transfer Learning based model (MIMCT) to detect offensive (hate speech or abusive) Hinglish tweets from the proposed Hinglish Offensive Tweet (HOT) dataset using transfer learning coupled with multiple feature inputs. Specifically, it takes multiple primary word embedding along with secondary extracted features as inputs to train a multi-channel CNN-LSTM architecture that has been pre-trained on English tweets through transfer learning. The proposed MIMCT model outperforms the baseline supervised classification models, transfer learning based CNN and LSTM models to establish itself as the state of the art in the unexplored domain of Hinglish offensive text classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mathur-etal-2018-offend">
<titleInfo>
<title>Did you offend me? Classification of Offensive Tweets in Hinglish Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Puneet</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramit</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghna</namePart>
<namePart type="family">Ayyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">Voigt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Waseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacqueline</namePart>
<namePart type="family">Wernimont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The use of code-switched languages (e.g., Hinglish, which is derived by the blending of Hindi with the English language) is getting much popular on Twitter due to their ease of communication in native languages. However, spelling variations and absence of grammar rules introduce ambiguity and make it difficult to understand the text automatically. This paper presents the Multi-Input Multi-Channel Transfer Learning based model (MIMCT) to detect offensive (hate speech or abusive) Hinglish tweets from the proposed Hinglish Offensive Tweet (HOT) dataset using transfer learning coupled with multiple feature inputs. Specifically, it takes multiple primary word embedding along with secondary extracted features as inputs to train a multi-channel CNN-LSTM architecture that has been pre-trained on English tweets through transfer learning. The proposed MIMCT model outperforms the baseline supervised classification models, transfer learning based CNN and LSTM models to establish itself as the state of the art in the unexplored domain of Hinglish offensive text classification.</abstract>
<identifier type="citekey">mathur-etal-2018-offend</identifier>
<identifier type="doi">10.18653/v1/W18-5118</identifier>
<location>
<url>https://aclanthology.org/W18-5118</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>138</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Did you offend me? Classification of Offensive Tweets in Hinglish Language
%A Mathur, Puneet
%A Sawhney, Ramit
%A Ayyar, Meghna
%A Shah, Rajiv
%Y Fišer, Darja
%Y Huang, Ruihong
%Y Prabhakaran, Vinodkumar
%Y Voigt, Rob
%Y Waseem, Zeerak
%Y Wernimont, Jacqueline
%S Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F mathur-etal-2018-offend
%X The use of code-switched languages (e.g., Hinglish, which is derived by the blending of Hindi with the English language) is getting much popular on Twitter due to their ease of communication in native languages. However, spelling variations and absence of grammar rules introduce ambiguity and make it difficult to understand the text automatically. This paper presents the Multi-Input Multi-Channel Transfer Learning based model (MIMCT) to detect offensive (hate speech or abusive) Hinglish tweets from the proposed Hinglish Offensive Tweet (HOT) dataset using transfer learning coupled with multiple feature inputs. Specifically, it takes multiple primary word embedding along with secondary extracted features as inputs to train a multi-channel CNN-LSTM architecture that has been pre-trained on English tweets through transfer learning. The proposed MIMCT model outperforms the baseline supervised classification models, transfer learning based CNN and LSTM models to establish itself as the state of the art in the unexplored domain of Hinglish offensive text classification.
%R 10.18653/v1/W18-5118
%U https://aclanthology.org/W18-5118
%U https://doi.org/10.18653/v1/W18-5118
%P 138-148
Markdown (Informal)
[Did you offend me? Classification of Offensive Tweets in Hinglish Language](https://aclanthology.org/W18-5118) (Mathur et al., ALW 2018)
ACL