@inproceedings{begum-etal-2016-functions,
title = "Functions of Code-Switching in Tweets: An Annotation Framework and Some Initial Experiments",
author = "Begum, Rafiya and
Bali, Kalika and
Choudhury, Monojit and
Rudra, Koustav and
Ganguly, Niloy",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1260",
pages = "1644--1650",
abstract = "Code-Switching (CS) between two languages is extremely common in communities with societal multilingualism where speakers switch between two or more languages when interacting with each other. CS has been extensively studied in spoken language by linguists for several decades but with the popularity of social-media and less formal Computer Mediated Communication, we now see a big rise in the use of CS in the text form. This poses interesting challenges and a need for computational processing of such code-switched data. As with any Computational Linguistic analysis and Natural Language Processing tools and applications, we need annotated data for understanding, processing, and generation of code-switched language. In this study, we focus on CS between English and Hindi Tweets extracted from the Twitter stream of Hindi-English bilinguals. We present an annotation scheme for annotating the pragmatic functions of CS in Hindi-English (Hi-En) code-switched tweets based on a linguistic analysis and some initial experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="begum-etal-2016-functions">
<titleInfo>
<title>Functions of Code-Switching in Tweets: An Annotation Framework and Some Initial Experiments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafiya</namePart>
<namePart type="family">Begum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustav</namePart>
<namePart type="family">Rudra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-Switching (CS) between two languages is extremely common in communities with societal multilingualism where speakers switch between two or more languages when interacting with each other. CS has been extensively studied in spoken language by linguists for several decades but with the popularity of social-media and less formal Computer Mediated Communication, we now see a big rise in the use of CS in the text form. This poses interesting challenges and a need for computational processing of such code-switched data. As with any Computational Linguistic analysis and Natural Language Processing tools and applications, we need annotated data for understanding, processing, and generation of code-switched language. In this study, we focus on CS between English and Hindi Tweets extracted from the Twitter stream of Hindi-English bilinguals. We present an annotation scheme for annotating the pragmatic functions of CS in Hindi-English (Hi-En) code-switched tweets based on a linguistic analysis and some initial experiments.</abstract>
<identifier type="citekey">begum-etal-2016-functions</identifier>
<location>
<url>https://aclanthology.org/L16-1260</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1644</start>
<end>1650</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Functions of Code-Switching in Tweets: An Annotation Framework and Some Initial Experiments
%A Begum, Rafiya
%A Bali, Kalika
%A Choudhury, Monojit
%A Rudra, Koustav
%A Ganguly, Niloy
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F begum-etal-2016-functions
%X Code-Switching (CS) between two languages is extremely common in communities with societal multilingualism where speakers switch between two or more languages when interacting with each other. CS has been extensively studied in spoken language by linguists for several decades but with the popularity of social-media and less formal Computer Mediated Communication, we now see a big rise in the use of CS in the text form. This poses interesting challenges and a need for computational processing of such code-switched data. As with any Computational Linguistic analysis and Natural Language Processing tools and applications, we need annotated data for understanding, processing, and generation of code-switched language. In this study, we focus on CS between English and Hindi Tweets extracted from the Twitter stream of Hindi-English bilinguals. We present an annotation scheme for annotating the pragmatic functions of CS in Hindi-English (Hi-En) code-switched tweets based on a linguistic analysis and some initial experiments.
%U https://aclanthology.org/L16-1260
%P 1644-1650
Markdown (Informal)
[Functions of Code-Switching in Tweets: An Annotation Framework and Some Initial Experiments](https://aclanthology.org/L16-1260) (Begum et al., LREC 2016)
ACL