@inproceedings{shimizu-etal-2014-collection,
title = "Collection of a Simultaneous Translation Corpus for Comparative Analysis",
author = "Shimizu, Hiroaki and
Neubig, Graham and
Sakti, Sakriani and
Toda, Tomoki and
Nakamura, Satoshi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/162_Paper.pdf",
pages = "670--673",
abstract = "This paper describes the collection of an English-Japanese/Japanese-English simultaneous interpretation corpus. There are two main features of the corpus. The first is that professional simultaneous interpreters with different amounts of experience cooperated with the collection. By comparing data from simultaneous interpretation of each interpreter, it is possible to compare better interpretations to those that are not as good. The second is that for part of our corpus there are already translation data available. This makes it possible to compare translation data with simultaneous interpretation data. We recorded the interpretations of lectures and news, and created time-aligned transcriptions. A total of 387k words of transcribed data were collected. The corpus will be helpful to analyze differences in interpretations styles and to construct simultaneous interpretation systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shimizu-etal-2014-collection">
<titleInfo>
<title>Collection of a Simultaneous Translation Corpus for Comparative Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Shimizu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Toda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the collection of an English-Japanese/Japanese-English simultaneous interpretation corpus. There are two main features of the corpus. The first is that professional simultaneous interpreters with different amounts of experience cooperated with the collection. By comparing data from simultaneous interpretation of each interpreter, it is possible to compare better interpretations to those that are not as good. The second is that for part of our corpus there are already translation data available. This makes it possible to compare translation data with simultaneous interpretation data. We recorded the interpretations of lectures and news, and created time-aligned transcriptions. A total of 387k words of transcribed data were collected. The corpus will be helpful to analyze differences in interpretations styles and to construct simultaneous interpretation systems.</abstract>
<identifier type="citekey">shimizu-etal-2014-collection</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/162_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>670</start>
<end>673</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collection of a Simultaneous Translation Corpus for Comparative Analysis
%A Shimizu, Hiroaki
%A Neubig, Graham
%A Sakti, Sakriani
%A Toda, Tomoki
%A Nakamura, Satoshi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F shimizu-etal-2014-collection
%X This paper describes the collection of an English-Japanese/Japanese-English simultaneous interpretation corpus. There are two main features of the corpus. The first is that professional simultaneous interpreters with different amounts of experience cooperated with the collection. By comparing data from simultaneous interpretation of each interpreter, it is possible to compare better interpretations to those that are not as good. The second is that for part of our corpus there are already translation data available. This makes it possible to compare translation data with simultaneous interpretation data. We recorded the interpretations of lectures and news, and created time-aligned transcriptions. A total of 387k words of transcribed data were collected. The corpus will be helpful to analyze differences in interpretations styles and to construct simultaneous interpretation systems.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/162_Paper.pdf
%P 670-673
Markdown (Informal)
[Collection of a Simultaneous Translation Corpus for Comparative Analysis](http://www.lrec-conf.org/proceedings/lrec2014/pdf/162_Paper.pdf) (Shimizu et al., LREC 2014)
ACL