@inproceedings{doi-etal-2021-large,
title = "Large-Scale {E}nglish-{J}apanese Simultaneous Interpretation Corpus: Construction and Analyses with Sentence-Aligned Data",
author = "Doi, Kosuke and
Sudoh, Katsuhito and
Nakamura, Satoshi",
editor = "Federico, Marcello and
Waibel, Alex and
Costa-juss{\`a}, Marta R. and
Niehues, Jan and
Stuker, Sebastian and
Salesky, Elizabeth",
booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
month = aug,
year = "2021",
address = "Bangkok, Thailand (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwslt-1.27/",
doi = "10.18653/v1/2021.iwslt-1.27",
pages = "226--235",
abstract = "This paper describes the construction of a new large-scale English-Japanese Simultaneous Interpretation (SI) corpus and presents the results of its analysis. A portion of the corpus contains SI data from three interpreters with different amounts of experience. Some of the SI data were manually aligned with the source speeches at the sentence level. Their latency, quality, and word order aspects were compared among the SI data themselves as well as against offline translations. The results showed that (1) interpreters with more experience controlled the latency and quality better, and (2) large latency hurt the SI quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doi-etal-2021-large">
<titleInfo>
<title>Large-Scale English-Japanese Simultaneous Interpretation Corpus: Construction and Analyses with Sentence-Aligned Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Doi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</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>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stuker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the construction of a new large-scale English-Japanese Simultaneous Interpretation (SI) corpus and presents the results of its analysis. A portion of the corpus contains SI data from three interpreters with different amounts of experience. Some of the SI data were manually aligned with the source speeches at the sentence level. Their latency, quality, and word order aspects were compared among the SI data themselves as well as against offline translations. The results showed that (1) interpreters with more experience controlled the latency and quality better, and (2) large latency hurt the SI quality.</abstract>
<identifier type="citekey">doi-etal-2021-large</identifier>
<identifier type="doi">10.18653/v1/2021.iwslt-1.27</identifier>
<location>
<url>https://aclanthology.org/2021.iwslt-1.27/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>226</start>
<end>235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large-Scale English-Japanese Simultaneous Interpretation Corpus: Construction and Analyses with Sentence-Aligned Data
%A Doi, Kosuke
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%Y Federico, Marcello
%Y Waibel, Alex
%Y Costa-jussà, Marta R.
%Y Niehues, Jan
%Y Stuker, Sebastian
%Y Salesky, Elizabeth
%S Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (online)
%F doi-etal-2021-large
%X This paper describes the construction of a new large-scale English-Japanese Simultaneous Interpretation (SI) corpus and presents the results of its analysis. A portion of the corpus contains SI data from three interpreters with different amounts of experience. Some of the SI data were manually aligned with the source speeches at the sentence level. Their latency, quality, and word order aspects were compared among the SI data themselves as well as against offline translations. The results showed that (1) interpreters with more experience controlled the latency and quality better, and (2) large latency hurt the SI quality.
%R 10.18653/v1/2021.iwslt-1.27
%U https://aclanthology.org/2021.iwslt-1.27/
%U https://doi.org/10.18653/v1/2021.iwslt-1.27
%P 226-235
Markdown (Informal)
[Large-Scale English-Japanese Simultaneous Interpretation Corpus: Construction and Analyses with Sentence-Aligned Data](https://aclanthology.org/2021.iwslt-1.27/) (Doi et al., IWSLT 2021)
ACL