@inproceedings{nguyen-bryant-2020-canvec,
title = "{C}an{VEC} - the Canberra {V}ietnamese-{E}nglish Code-switching Natural Speech Corpus",
author = "Nguyen, Li and
Bryant, Christopher",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.507/",
pages = "4121--4129",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "This paper introduces the Canberra Vietnamese-English Code-switching corpus (CanVEC), an original corpus of natural mixed speech that we semi-automatically annotated with language information, part of speech (POS) tags and Vietnamese translations. The corpus, which was built to inform a sociolinguistic study on language variation and code-switching, consists of 10 hours of recorded speech (87k tokens) between 45 Vietnamese-English bilinguals living in Canberra, Australia. We describe how we collected and annotated the corpus by pipelining several monolingual toolkits to considerably speed up the annotation process. We also describe how we evaluated the automatic annotations to ensure corpus reliability. We make the corpus available for research purposes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-bryant-2020-canvec">
<titleInfo>
<title>CanVEC - the Canberra Vietnamese-English Code-switching Natural Speech Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Bryant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper introduces the Canberra Vietnamese-English Code-switching corpus (CanVEC), an original corpus of natural mixed speech that we semi-automatically annotated with language information, part of speech (POS) tags and Vietnamese translations. The corpus, which was built to inform a sociolinguistic study on language variation and code-switching, consists of 10 hours of recorded speech (87k tokens) between 45 Vietnamese-English bilinguals living in Canberra, Australia. We describe how we collected and annotated the corpus by pipelining several monolingual toolkits to considerably speed up the annotation process. We also describe how we evaluated the automatic annotations to ensure corpus reliability. We make the corpus available for research purposes.</abstract>
<identifier type="citekey">nguyen-bryant-2020-canvec</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.507/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4121</start>
<end>4129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CanVEC - the Canberra Vietnamese-English Code-switching Natural Speech Corpus
%A Nguyen, Li
%A Bryant, Christopher
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F nguyen-bryant-2020-canvec
%X This paper introduces the Canberra Vietnamese-English Code-switching corpus (CanVEC), an original corpus of natural mixed speech that we semi-automatically annotated with language information, part of speech (POS) tags and Vietnamese translations. The corpus, which was built to inform a sociolinguistic study on language variation and code-switching, consists of 10 hours of recorded speech (87k tokens) between 45 Vietnamese-English bilinguals living in Canberra, Australia. We describe how we collected and annotated the corpus by pipelining several monolingual toolkits to considerably speed up the annotation process. We also describe how we evaluated the automatic annotations to ensure corpus reliability. We make the corpus available for research purposes.
%U https://aclanthology.org/2020.lrec-1.507/
%P 4121-4129
Markdown (Informal)
[CanVEC - the Canberra Vietnamese-English Code-switching Natural Speech Corpus](https://aclanthology.org/2020.lrec-1.507/) (Nguyen & Bryant, LREC 2020)
ACL