@inproceedings{yasuda-etal-2011-annotating,
title = "Annotating data selection for improving machine translation",
author = "Yasuda, Keiji and
Okuma, Hideo and
Utiyama, Masao and
Sumita, Eiichiro",
booktitle = "Proceedings of the 8th International Workshop on Spoken Language Translation: Papers",
month = dec # " 8-9",
year = "2011",
address = "San Francisco, California",
url = "https://aclanthology.org/2011.iwslt-papers.11",
pages = "269--274",
abstract = "In order to efficiently improve machine translation systems, we propose a method which selects data to be annotated (manually translated) from speech-to-speech translation field data. For the selection experiments, we used data from field experiments conducted during the 2009 fiscal year in five areas of Japan. For the selection experiments, we used data sets from two areas: one data set giving the lowest baseline speech translation performance for its test set, and another data set giving the highest. In the experiments, we compare two methods for selecting data to be manually translated from the field data. Both of them use source side language models for data selection, but in different manners. According to the experimental results, either or both of the methods show larger improvements compared to a random data selection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yasuda-etal-2011-annotating">
<titleInfo>
<title>Annotating data selection for improving machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keiji</namePart>
<namePart type="family">Yasuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideo</namePart>
<namePart type="family">Okuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2011-dec" 8-9"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th International Workshop on Spoken Language Translation: Papers</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">San Francisco, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In order to efficiently improve machine translation systems, we propose a method which selects data to be annotated (manually translated) from speech-to-speech translation field data. For the selection experiments, we used data from field experiments conducted during the 2009 fiscal year in five areas of Japan. For the selection experiments, we used data sets from two areas: one data set giving the lowest baseline speech translation performance for its test set, and another data set giving the highest. In the experiments, we compare two methods for selecting data to be manually translated from the field data. Both of them use source side language models for data selection, but in different manners. According to the experimental results, either or both of the methods show larger improvements compared to a random data selection.</abstract>
<identifier type="citekey">yasuda-etal-2011-annotating</identifier>
<location>
<url>https://aclanthology.org/2011.iwslt-papers.11</url>
</location>
<part>
<date>2011-dec" 8-9"</date>
<extent unit="page">
<start>269</start>
<end>274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating data selection for improving machine translation
%A Yasuda, Keiji
%A Okuma, Hideo
%A Utiyama, Masao
%A Sumita, Eiichiro
%S Proceedings of the 8th International Workshop on Spoken Language Translation: Papers
%D 2011
%8 dec" 8 9"
%C San Francisco, California
%F yasuda-etal-2011-annotating
%X In order to efficiently improve machine translation systems, we propose a method which selects data to be annotated (manually translated) from speech-to-speech translation field data. For the selection experiments, we used data from field experiments conducted during the 2009 fiscal year in five areas of Japan. For the selection experiments, we used data sets from two areas: one data set giving the lowest baseline speech translation performance for its test set, and another data set giving the highest. In the experiments, we compare two methods for selecting data to be manually translated from the field data. Both of them use source side language models for data selection, but in different manners. According to the experimental results, either or both of the methods show larger improvements compared to a random data selection.
%U https://aclanthology.org/2011.iwslt-papers.11
%P 269-274
Markdown (Informal)
[Annotating data selection for improving machine translation](https://aclanthology.org/2011.iwslt-papers.11) (Yasuda et al., IWSLT 2011)
ACL