@inproceedings{raihan-etal-2024-emomix,
title = "{E}mo{M}ix-3{L}: A Code-Mixed Dataset for {B}angla-{E}nglish-{H}indi for Emotion Detection",
author = "Raihan, Nishat and
Goswami, Dhiman and
Mahmud, Antara and
Anastasopoulos, Antonios and
Zampieri, Marcos",
editor = "Jha, Girish Nath and
L., Sobha and
Bali, Kalika and
Ojha, Atul Kr.",
booktitle = "Proceedings of the 7th Workshop on Indian Language Data: Resources and Evaluation",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.wildre-1.2",
pages = "11--16",
abstract = "Code-mixing is a well-studied linguistic phenomenon that occurs when two or more languages are mixed in text or speech. Several studies have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce EmoMix-3L, a novel multi-label emotion detection dataset containing code-mixed data from three different languages. We experiment with several models on EmoMix-3L and we report that MuRIL outperforms other models on this dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raihan-etal-2024-emomix">
<titleInfo>
<title>EmoMix-3L: A Code-Mixed Dataset for Bangla-English-Hindi for Emotion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nishat</namePart>
<namePart type="family">Raihan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhiman</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antara</namePart>
<namePart type="family">Mahmud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Indian Language Data: Resources and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L.</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">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-mixing is a well-studied linguistic phenomenon that occurs when two or more languages are mixed in text or speech. Several studies have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce EmoMix-3L, a novel multi-label emotion detection dataset containing code-mixed data from three different languages. We experiment with several models on EmoMix-3L and we report that MuRIL outperforms other models on this dataset.</abstract>
<identifier type="citekey">raihan-etal-2024-emomix</identifier>
<location>
<url>https://aclanthology.org/2024.wildre-1.2</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmoMix-3L: A Code-Mixed Dataset for Bangla-English-Hindi for Emotion Detection
%A Raihan, Nishat
%A Goswami, Dhiman
%A Mahmud, Antara
%A Anastasopoulos, Antonios
%A Zampieri, Marcos
%Y Jha, Girish Nath
%Y L., Sobha
%Y Bali, Kalika
%Y Ojha, Atul Kr.
%S Proceedings of the 7th Workshop on Indian Language Data: Resources and Evaluation
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F raihan-etal-2024-emomix
%X Code-mixing is a well-studied linguistic phenomenon that occurs when two or more languages are mixed in text or speech. Several studies have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce EmoMix-3L, a novel multi-label emotion detection dataset containing code-mixed data from three different languages. We experiment with several models on EmoMix-3L and we report that MuRIL outperforms other models on this dataset.
%U https://aclanthology.org/2024.wildre-1.2
%P 11-16
Markdown (Informal)
[EmoMix-3L: A Code-Mixed Dataset for Bangla-English-Hindi for Emotion Detection](https://aclanthology.org/2024.wildre-1.2) (Raihan et al., WILDRE-WS 2024)
ACL