@inproceedings{chathuranga-ranathunga-2021-classification,
title = "Classification of Code-Mixed Text Using Capsule Networks",
author = "Chathuranga, Shanaka and
Ranathunga, Surangika",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.30",
pages = "256--263",
abstract = "A major challenge in analysing social me-dia data belonging to languages that use non-English script is its code-mixed nature. Recentresearch has presented state-of-the-art contex-tual embedding models (both monolingual s.a.BERT and multilingual s.a.XLM-R) as apromising approach. In this paper, we showthat the performance of such embedding mod-els depends on multiple factors, such as thelevel of code-mixing in the dataset, and thesize of the training dataset. We empiricallyshow that a newly introduced Capsule+biGRUclassifier could outperform a classifier built onthe English-BERT as well as XLM-R just witha training dataset of about 6500 samples forthe Sinhala-English code-mixed data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chathuranga-ranathunga-2021-classification">
<titleInfo>
<title>Classification of Code-Mixed Text Using Capsule Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shanaka</namePart>
<namePart type="family">Chathuranga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surangika</namePart>
<namePart type="family">Ranathunga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A major challenge in analysing social me-dia data belonging to languages that use non-English script is its code-mixed nature. Recentresearch has presented state-of-the-art contex-tual embedding models (both monolingual s.a.BERT and multilingual s.a.XLM-R) as apromising approach. In this paper, we showthat the performance of such embedding mod-els depends on multiple factors, such as thelevel of code-mixing in the dataset, and thesize of the training dataset. We empiricallyshow that a newly introduced Capsule+biGRUclassifier could outperform a classifier built onthe English-BERT as well as XLM-R just witha training dataset of about 6500 samples forthe Sinhala-English code-mixed data.</abstract>
<identifier type="citekey">chathuranga-ranathunga-2021-classification</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.30</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>256</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Classification of Code-Mixed Text Using Capsule Networks
%A Chathuranga, Shanaka
%A Ranathunga, Surangika
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F chathuranga-ranathunga-2021-classification
%X A major challenge in analysing social me-dia data belonging to languages that use non-English script is its code-mixed nature. Recentresearch has presented state-of-the-art contex-tual embedding models (both monolingual s.a.BERT and multilingual s.a.XLM-R) as apromising approach. In this paper, we showthat the performance of such embedding mod-els depends on multiple factors, such as thelevel of code-mixing in the dataset, and thesize of the training dataset. We empiricallyshow that a newly introduced Capsule+biGRUclassifier could outperform a classifier built onthe English-BERT as well as XLM-R just witha training dataset of about 6500 samples forthe Sinhala-English code-mixed data.
%U https://aclanthology.org/2021.ranlp-1.30
%P 256-263
Markdown (Informal)
[Classification of Code-Mixed Text Using Capsule Networks](https://aclanthology.org/2021.ranlp-1.30) (Chathuranga & Ranathunga, RANLP 2021)
ACL