@inproceedings{zhou-etal-2010-casia,
title = "{CASIA}-{CASSIL}: a {C}hinese Telephone Conversation Corpus in Real Scenarios with Multi-leveled Annotation",
author = "Zhou, Keyan and
Li, Aijun and
Yin, Zhigang and
Zong, Chengqing",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/248_Paper.pdf",
abstract = "CASIA-CASSIL is a large-scale corpus base of Chinese human-human naturally-occurring telephone conversations in restricted domains. The first edition consists of 792 90-second conversations belonging to tourism domain, which are selected from 7,639 spontaneous telephone recordings in real scenarios. The corpus is now being annotated with wide range of linguistic and paralinguistic information in multi-levels. The annotations include Turns, Speaker Gender, Orthographic Transcription, Chinese Syllable, Chinese Phonetic Transcription, Prosodic Boundary, Stress of Sentence, Non-Speech Sounds, Voice Quality, Topic, Dialog-act and Adjacency Pairs, Ill-formedness, and Expressive Emotion as well, 13 levels in total. The abundant annotation will be effective especially for studying Chinese spoken language phenomena. This paper describes the whole process to build the conversation corpus, including collecting and selecting the original data, and the follow-up process such as transcribing, annotating, and so on. CASIA-CASSIL is being extended to a large scale corpus base of annotated Chinese dialogs for spoken Chinese study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2010-casia">
<titleInfo>
<title>CASIA-CASSIL: a Chinese Telephone Conversation Corpus in Real Scenarios with Multi-leveled Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keyan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aijun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhigang</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>CASIA-CASSIL is a large-scale corpus base of Chinese human-human naturally-occurring telephone conversations in restricted domains. The first edition consists of 792 90-second conversations belonging to tourism domain, which are selected from 7,639 spontaneous telephone recordings in real scenarios. The corpus is now being annotated with wide range of linguistic and paralinguistic information in multi-levels. The annotations include Turns, Speaker Gender, Orthographic Transcription, Chinese Syllable, Chinese Phonetic Transcription, Prosodic Boundary, Stress of Sentence, Non-Speech Sounds, Voice Quality, Topic, Dialog-act and Adjacency Pairs, Ill-formedness, and Expressive Emotion as well, 13 levels in total. The abundant annotation will be effective especially for studying Chinese spoken language phenomena. This paper describes the whole process to build the conversation corpus, including collecting and selecting the original data, and the follow-up process such as transcribing, annotating, and so on. CASIA-CASSIL is being extended to a large scale corpus base of annotated Chinese dialogs for spoken Chinese study.</abstract>
<identifier type="citekey">zhou-etal-2010-casia</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/248_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CASIA-CASSIL: a Chinese Telephone Conversation Corpus in Real Scenarios with Multi-leveled Annotation
%A Zhou, Keyan
%A Li, Aijun
%A Yin, Zhigang
%A Zong, Chengqing
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F zhou-etal-2010-casia
%X CASIA-CASSIL is a large-scale corpus base of Chinese human-human naturally-occurring telephone conversations in restricted domains. The first edition consists of 792 90-second conversations belonging to tourism domain, which are selected from 7,639 spontaneous telephone recordings in real scenarios. The corpus is now being annotated with wide range of linguistic and paralinguistic information in multi-levels. The annotations include Turns, Speaker Gender, Orthographic Transcription, Chinese Syllable, Chinese Phonetic Transcription, Prosodic Boundary, Stress of Sentence, Non-Speech Sounds, Voice Quality, Topic, Dialog-act and Adjacency Pairs, Ill-formedness, and Expressive Emotion as well, 13 levels in total. The abundant annotation will be effective especially for studying Chinese spoken language phenomena. This paper describes the whole process to build the conversation corpus, including collecting and selecting the original data, and the follow-up process such as transcribing, annotating, and so on. CASIA-CASSIL is being extended to a large scale corpus base of annotated Chinese dialogs for spoken Chinese study.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/248_Paper.pdf
Markdown (Informal)
[CASIA-CASSIL: a Chinese Telephone Conversation Corpus in Real Scenarios with Multi-leveled Annotation](http://www.lrec-conf.org/proceedings/lrec2010/pdf/248_Paper.pdf) (Zhou et al., LREC 2010)
ACL