@inproceedings{dowlagar-mamidi-2021-pre,
title = "A Pre-trained Transformer and {CNN} Model with Joint Language {ID} and Part-of-Speech Tagging for Code-Mixed Social-Media Text",
author = "Dowlagar, Suman and
Mamidi, Radhika",
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-1.42",
pages = "367--374",
abstract = "Code-mixing (CM) is a frequently observed phenomenon that uses multiple languages in an utterance or sentence. There are no strict grammatical constraints observed in code-mixing, and it consists of non-standard variations of spelling. The linguistic complexity resulting from the above factors made the computational analysis of the code-mixed language a challenging task. Language identification (LI) and part of speech (POS) tagging are the fundamental steps that help analyze the structure of the code-mixed text. Often, the LI and POS tagging tasks are interdependent in the code-mixing scenario. We project the problem of dealing with multilingualism and grammatical structure while analyzing the code-mixed sentence as a joint learning task. In this paper, we jointly train and optimize language detection and part of speech tagging models in the code-mixed scenario. We used a Transformer with convolutional neural network architecture. We train a joint learning method by combining POS tagging and LI models on code-mixed social media text obtained from the ICON shared task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dowlagar-mamidi-2021-pre">
<titleInfo>
<title>A Pre-trained Transformer and CNN Model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suman</namePart>
<namePart type="family">Dowlagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Mamidi</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>Code-mixing (CM) is a frequently observed phenomenon that uses multiple languages in an utterance or sentence. There are no strict grammatical constraints observed in code-mixing, and it consists of non-standard variations of spelling. The linguistic complexity resulting from the above factors made the computational analysis of the code-mixed language a challenging task. Language identification (LI) and part of speech (POS) tagging are the fundamental steps that help analyze the structure of the code-mixed text. Often, the LI and POS tagging tasks are interdependent in the code-mixing scenario. We project the problem of dealing with multilingualism and grammatical structure while analyzing the code-mixed sentence as a joint learning task. In this paper, we jointly train and optimize language detection and part of speech tagging models in the code-mixed scenario. We used a Transformer with convolutional neural network architecture. We train a joint learning method by combining POS tagging and LI models on code-mixed social media text obtained from the ICON shared task.</abstract>
<identifier type="citekey">dowlagar-mamidi-2021-pre</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.42</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>367</start>
<end>374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Pre-trained Transformer and CNN Model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text
%A Dowlagar, Suman
%A Mamidi, Radhika
%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 dowlagar-mamidi-2021-pre
%X Code-mixing (CM) is a frequently observed phenomenon that uses multiple languages in an utterance or sentence. There are no strict grammatical constraints observed in code-mixing, and it consists of non-standard variations of spelling. The linguistic complexity resulting from the above factors made the computational analysis of the code-mixed language a challenging task. Language identification (LI) and part of speech (POS) tagging are the fundamental steps that help analyze the structure of the code-mixed text. Often, the LI and POS tagging tasks are interdependent in the code-mixing scenario. We project the problem of dealing with multilingualism and grammatical structure while analyzing the code-mixed sentence as a joint learning task. In this paper, we jointly train and optimize language detection and part of speech tagging models in the code-mixed scenario. We used a Transformer with convolutional neural network architecture. We train a joint learning method by combining POS tagging and LI models on code-mixed social media text obtained from the ICON shared task.
%U https://aclanthology.org/2021.ranlp-1.42
%P 367-374
Markdown (Informal)
[A Pre-trained Transformer and CNN Model with Joint Language ID and Part-of-Speech Tagging for Code-Mixed Social-Media Text](https://aclanthology.org/2021.ranlp-1.42) (Dowlagar & Mamidi, RANLP 2021)
ACL