@inproceedings{winterstein-etal-2020-cantomap,
title = "{C}anto{M}ap: a {H}ong {K}ong {C}antonese {M}ap{T}ask Corpus",
author = "Winterstein, Gr{\'e}goire and
Tang, Carmen and
Lai, Regine",
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-1.355",
pages = "2906--2913",
abstract = "This work reports on the construction of a corpus of connected spoken Hong Kong Cantonese. The corpus aims at providing an additional resource for the study of modern (Hong Kong) Cantonese and also involves several controlled elicitation tasks which will serve different projects related to the phonology and semantics of Cantonese. The word-segmented corpus offers recordings, phonemic transcription, and Chinese characters transcription. The corpus contains a total of 768 minutes of recordings and transcripts of forty speakers. All the audio material has been aligned at utterance level with the transcriptions, using the ELAN transcription and annotation tool. The controlled elicitation task was based on the design of HCRC MapTask corpus (Anderson et al., 1991), in which participants had to communicate using solely verbal means as eye contact was restricted. In this paper, we outline the design of the maps and their landmarks and the basic segmentation principles of the data and various transcription conventions we adopted. We also compare the contents of Cantomap to those of comparable Cantonese corpora.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winterstein-etal-2020-cantomap">
<titleInfo>
<title>CantoMap: a Hong Kong Cantonese MapTask Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Grégoire</namePart>
<namePart type="family">Winterstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carmen</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regine</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">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 work reports on the construction of a corpus of connected spoken Hong Kong Cantonese. The corpus aims at providing an additional resource for the study of modern (Hong Kong) Cantonese and also involves several controlled elicitation tasks which will serve different projects related to the phonology and semantics of Cantonese. The word-segmented corpus offers recordings, phonemic transcription, and Chinese characters transcription. The corpus contains a total of 768 minutes of recordings and transcripts of forty speakers. All the audio material has been aligned at utterance level with the transcriptions, using the ELAN transcription and annotation tool. The controlled elicitation task was based on the design of HCRC MapTask corpus (Anderson et al., 1991), in which participants had to communicate using solely verbal means as eye contact was restricted. In this paper, we outline the design of the maps and their landmarks and the basic segmentation principles of the data and various transcription conventions we adopted. We also compare the contents of Cantomap to those of comparable Cantonese corpora.</abstract>
<identifier type="citekey">winterstein-etal-2020-cantomap</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.355</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2906</start>
<end>2913</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CantoMap: a Hong Kong Cantonese MapTask Corpus
%A Winterstein, Grégoire
%A Tang, Carmen
%A Lai, Regine
%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 English
%F winterstein-etal-2020-cantomap
%X This work reports on the construction of a corpus of connected spoken Hong Kong Cantonese. The corpus aims at providing an additional resource for the study of modern (Hong Kong) Cantonese and also involves several controlled elicitation tasks which will serve different projects related to the phonology and semantics of Cantonese. The word-segmented corpus offers recordings, phonemic transcription, and Chinese characters transcription. The corpus contains a total of 768 minutes of recordings and transcripts of forty speakers. All the audio material has been aligned at utterance level with the transcriptions, using the ELAN transcription and annotation tool. The controlled elicitation task was based on the design of HCRC MapTask corpus (Anderson et al., 1991), in which participants had to communicate using solely verbal means as eye contact was restricted. In this paper, we outline the design of the maps and their landmarks and the basic segmentation principles of the data and various transcription conventions we adopted. We also compare the contents of Cantomap to those of comparable Cantonese corpora.
%U https://aclanthology.org/2020.lrec-1.355
%P 2906-2913
Markdown (Informal)
[CantoMap: a Hong Kong Cantonese MapTask Corpus](https://aclanthology.org/2020.lrec-1.355) (Winterstein et al., LREC 2020)
ACL
- Grégoire Winterstein, Carmen Tang, and Regine Lai. 2020. CantoMap: a Hong Kong Cantonese MapTask Corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2906–2913, Marseille, France. European Language Resources Association.