@inproceedings{aggarwal-etal-2020-really,
title = "{``}Did you really mean what you said?{''} : Sarcasm Detection in {H}indi-{E}nglish Code-Mixed Data using Bilingual Word Embeddings",
author = "Aggarwal, Akshita and
Wadhawan, Anshul and
Chaudhary, Anshima and
Maurya, Kavita",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.2",
doi = "10.18653/v1/2020.wnut-1.2",
pages = "7--15",
abstract = "With the increased use of social media platforms by people across the world, many new interesting NLP problems have come into existence. One such being the detection of sarcasm in the social media texts. We present a corpus of tweets for training custom word embeddings and a Hinglish dataset labelled for sarcasm detection. We propose a deep learning based approach to address the issue of sarcasm detection in Hindi-English code mixed tweets using bilingual word embeddings derived from FastText and Word2Vec approaches. We experimented with various deep learning models, including CNNs, LSTMs, Bi-directional LSTMs (with and without attention). We were able to outperform all state-of-the-art performances with our deep learning models, with attention based Bi-directional LSTMs giving the best performance exhibiting an accuracy of 78.49{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aggarwal-etal-2020-really">
<titleInfo>
<title>“Did you really mean what you said?” : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshita</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anshul</namePart>
<namePart type="family">Wadhawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anshima</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kavita</namePart>
<namePart type="family">Maurya</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 Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>With the increased use of social media platforms by people across the world, many new interesting NLP problems have come into existence. One such being the detection of sarcasm in the social media texts. We present a corpus of tweets for training custom word embeddings and a Hinglish dataset labelled for sarcasm detection. We propose a deep learning based approach to address the issue of sarcasm detection in Hindi-English code mixed tweets using bilingual word embeddings derived from FastText and Word2Vec approaches. We experimented with various deep learning models, including CNNs, LSTMs, Bi-directional LSTMs (with and without attention). We were able to outperform all state-of-the-art performances with our deep learning models, with attention based Bi-directional LSTMs giving the best performance exhibiting an accuracy of 78.49%.</abstract>
<identifier type="citekey">aggarwal-etal-2020-really</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.2</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.2</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>7</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “Did you really mean what you said?” : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings
%A Aggarwal, Akshita
%A Wadhawan, Anshul
%A Chaudhary, Anshima
%A Maurya, Kavita
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F aggarwal-etal-2020-really
%X With the increased use of social media platforms by people across the world, many new interesting NLP problems have come into existence. One such being the detection of sarcasm in the social media texts. We present a corpus of tweets for training custom word embeddings and a Hinglish dataset labelled for sarcasm detection. We propose a deep learning based approach to address the issue of sarcasm detection in Hindi-English code mixed tweets using bilingual word embeddings derived from FastText and Word2Vec approaches. We experimented with various deep learning models, including CNNs, LSTMs, Bi-directional LSTMs (with and without attention). We were able to outperform all state-of-the-art performances with our deep learning models, with attention based Bi-directional LSTMs giving the best performance exhibiting an accuracy of 78.49%.
%R 10.18653/v1/2020.wnut-1.2
%U https://aclanthology.org/2020.wnut-1.2
%U https://doi.org/10.18653/v1/2020.wnut-1.2
%P 7-15
Markdown (Informal)
[“Did you really mean what you said?” : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings](https://aclanthology.org/2020.wnut-1.2) (Aggarwal et al., WNUT 2020)
ACL