@inproceedings{li-etal-2012-mandarin,
title = "A {M}andarin-{E}nglish Code-Switching Corpus",
author = "Li, Ying and
Yu, Yue and
Fung, Pascale",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/964_Paper.pdf",
pages = "2515--2519",
abstract = "Generally the existing monolingual corpora are not suitable for large vocabulary continuous speech recognition (LVCSR) of code-switching speech. The motivation of this paper is to study the rules and constraints code-switching follows and design a corpus for code-switching LVCSR task. This paper presents the development of a Mandarin-English code-switching corpus. This corpus consists of four parts: 1) conversational meeting speech and its data; 2) project meeting speech data; 3) student interviews speech; 4) text data of on-line news. The speech was transcribed by an annotator and verified by Mandarin-English bilingual speakers manually. We propose an approach for automatically downloading from the web text data that contains code-switching. The corpus includes both intra-sentential code-switching (switch in the middle of a sentence) and inter-sentential code-switching (switch at the end of the sentence). The distribution of part-of-speech (POS) tags and code-switching reasons are reported.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2012-mandarin">
<titleInfo>
<title>A Mandarin-English Code-Switching Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generally the existing monolingual corpora are not suitable for large vocabulary continuous speech recognition (LVCSR) of code-switching speech. The motivation of this paper is to study the rules and constraints code-switching follows and design a corpus for code-switching LVCSR task. This paper presents the development of a Mandarin-English code-switching corpus. This corpus consists of four parts: 1) conversational meeting speech and its data; 2) project meeting speech data; 3) student interviews speech; 4) text data of on-line news. The speech was transcribed by an annotator and verified by Mandarin-English bilingual speakers manually. We propose an approach for automatically downloading from the web text data that contains code-switching. The corpus includes both intra-sentential code-switching (switch in the middle of a sentence) and inter-sentential code-switching (switch at the end of the sentence). The distribution of part-of-speech (POS) tags and code-switching reasons are reported.</abstract>
<identifier type="citekey">li-etal-2012-mandarin</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/964_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2515</start>
<end>2519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Mandarin-English Code-Switching Corpus
%A Li, Ying
%A Yu, Yue
%A Fung, Pascale
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F li-etal-2012-mandarin
%X Generally the existing monolingual corpora are not suitable for large vocabulary continuous speech recognition (LVCSR) of code-switching speech. The motivation of this paper is to study the rules and constraints code-switching follows and design a corpus for code-switching LVCSR task. This paper presents the development of a Mandarin-English code-switching corpus. This corpus consists of four parts: 1) conversational meeting speech and its data; 2) project meeting speech data; 3) student interviews speech; 4) text data of on-line news. The speech was transcribed by an annotator and verified by Mandarin-English bilingual speakers manually. We propose an approach for automatically downloading from the web text data that contains code-switching. The corpus includes both intra-sentential code-switching (switch in the middle of a sentence) and inter-sentential code-switching (switch at the end of the sentence). The distribution of part-of-speech (POS) tags and code-switching reasons are reported.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/964_Paper.pdf
%P 2515-2519
Markdown (Informal)
[A Mandarin-English Code-Switching Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/964_Paper.pdf) (Li et al., LREC 2012)
ACL
- Ying Li, Yue Yu, and Pascale Fung. 2012. A Mandarin-English Code-Switching Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2515–2519, Istanbul, Turkey. European Language Resources Association (ELRA).