@inproceedings{jayanthi-etal-2021-codemixednlp,
title = "{C}odemixed{NLP}: An Extensible and Open {NLP} Toolkit for Code-Mixing",
author = "Jayanthi, Sai Muralidhar and
Nerella, Kavya and
Chandu, Khyathi Raghavi and
Black, Alan W",
editor = "Solorio, Thamar and
Chen, Shuguang and
Black, Alan W. and
Diab, Mona and
Sitaram, Sunayana and
Soto, Victor and
Yilmaz, Emre and
Srinivasan, Anirudh",
booktitle = "Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.calcs-1.14",
doi = "10.18653/v1/2021.calcs-1.14",
pages = "113--118",
abstract = "The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on social media, have boosted interest in modeling code-mixed texts. In this work, we present CodemixedNLP, an open-source library with the goals of bringing together the advances in code-mixed NLP and opening it up to a wider machine learning community. The library consists of tools to develop and benchmark versatile model architectures that are tailored for mixed texts, methods to expand training sets, techniques to quantify mixing styles, and fine-tuned state-of-the-art models for 7 tasks in Hinglish. We believe this work has the potential to foster a distributed yet collaborative and sustainable ecosystem in an otherwise dispersed space of code-mixing research. The toolkit is designed to be simple, easily extensible, and resourceful to both researchers as well as practitioners. Demo: \url{http://k-ikkees.pc.cs.cmu.edu:5000} and Library: \url{https://github.com/murali1996/CodemixedNLP}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jayanthi-etal-2021-codemixednlp">
<titleInfo>
<title>CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Muralidhar</namePart>
<namePart type="family">Jayanthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kavya</namePart>
<namePart type="family">Nerella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Soto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emre</namePart>
<namePart type="family">Yilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirudh</namePart>
<namePart type="family">Srinivasan</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>The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on social media, have boosted interest in modeling code-mixed texts. In this work, we present CodemixedNLP, an open-source library with the goals of bringing together the advances in code-mixed NLP and opening it up to a wider machine learning community. The library consists of tools to develop and benchmark versatile model architectures that are tailored for mixed texts, methods to expand training sets, techniques to quantify mixing styles, and fine-tuned state-of-the-art models for 7 tasks in Hinglish. We believe this work has the potential to foster a distributed yet collaborative and sustainable ecosystem in an otherwise dispersed space of code-mixing research. The toolkit is designed to be simple, easily extensible, and resourceful to both researchers as well as practitioners. Demo: http://k-ikkees.pc.cs.cmu.edu:5000 and Library: https://github.com/murali1996/CodemixedNLP</abstract>
<identifier type="citekey">jayanthi-etal-2021-codemixednlp</identifier>
<identifier type="doi">10.18653/v1/2021.calcs-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.calcs-1.14</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>113</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing
%A Jayanthi, Sai Muralidhar
%A Nerella, Kavya
%A Chandu, Khyathi Raghavi
%A Black, Alan W.
%Y Solorio, Thamar
%Y Chen, Shuguang
%Y Black, Alan W.
%Y Diab, Mona
%Y Sitaram, Sunayana
%Y Soto, Victor
%Y Yilmaz, Emre
%Y Srinivasan, Anirudh
%S Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F jayanthi-etal-2021-codemixednlp
%X The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on social media, have boosted interest in modeling code-mixed texts. In this work, we present CodemixedNLP, an open-source library with the goals of bringing together the advances in code-mixed NLP and opening it up to a wider machine learning community. The library consists of tools to develop and benchmark versatile model architectures that are tailored for mixed texts, methods to expand training sets, techniques to quantify mixing styles, and fine-tuned state-of-the-art models for 7 tasks in Hinglish. We believe this work has the potential to foster a distributed yet collaborative and sustainable ecosystem in an otherwise dispersed space of code-mixing research. The toolkit is designed to be simple, easily extensible, and resourceful to both researchers as well as practitioners. Demo: http://k-ikkees.pc.cs.cmu.edu:5000 and Library: https://github.com/murali1996/CodemixedNLP
%R 10.18653/v1/2021.calcs-1.14
%U https://aclanthology.org/2021.calcs-1.14
%U https://doi.org/10.18653/v1/2021.calcs-1.14
%P 113-118
Markdown (Informal)
[CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing](https://aclanthology.org/2021.calcs-1.14) (Jayanthi et al., CALCS 2021)
ACL