@inproceedings{fujii-etal-2008-producing,
title = "Producing a Test Collection for Patent Machine Translation in the Seventh {NTCIR} Workshop",
author = "Fujii, Atsushi and
Utiyama, Masao and
Yamamoto, Mikio and
Utsuro, Takehito",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/458_paper.pdf",
abstract = "In aiming at research and development on machine translation, we produced a test collection for Japanese-English machine translation in the seventh NTCIR Workshop. This paper describes details of our test collection. From patent documents published in Japan and the United States, we extracted patent families as a parallel corpus. A patent family is a set of patent documents for the same or related invention and these documents are usually filed to more than one country in different languages. In the parallel corpus, we aligned Japanese sentences with their counterpart English sentences. Our test collection, which includes approximately 2,000,000 sentence pairs, can be used to train and test machine translation systems. Our test collection also includes search topics for cross-lingual patent retrieval and the contribution of machine translation to a patent retrieval task can also be evaluated. Our test collection will be available to the public for research purposes after the NTCIR final meeting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fujii-etal-2008-producing">
<titleInfo>
<title>Producing a Test Collection for Patent Machine Translation in the Seventh NTCIR Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Fujii</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">Mikio</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In aiming at research and development on machine translation, we produced a test collection for Japanese-English machine translation in the seventh NTCIR Workshop. This paper describes details of our test collection. From patent documents published in Japan and the United States, we extracted patent families as a parallel corpus. A patent family is a set of patent documents for the same or related invention and these documents are usually filed to more than one country in different languages. In the parallel corpus, we aligned Japanese sentences with their counterpart English sentences. Our test collection, which includes approximately 2,000,000 sentence pairs, can be used to train and test machine translation systems. Our test collection also includes search topics for cross-lingual patent retrieval and the contribution of machine translation to a patent retrieval task can also be evaluated. Our test collection will be available to the public for research purposes after the NTCIR final meeting.</abstract>
<identifier type="citekey">fujii-etal-2008-producing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/458_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Producing a Test Collection for Patent Machine Translation in the Seventh NTCIR Workshop
%A Fujii, Atsushi
%A Utiyama, Masao
%A Yamamoto, Mikio
%A Utsuro, Takehito
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F fujii-etal-2008-producing
%X In aiming at research and development on machine translation, we produced a test collection for Japanese-English machine translation in the seventh NTCIR Workshop. This paper describes details of our test collection. From patent documents published in Japan and the United States, we extracted patent families as a parallel corpus. A patent family is a set of patent documents for the same or related invention and these documents are usually filed to more than one country in different languages. In the parallel corpus, we aligned Japanese sentences with their counterpart English sentences. Our test collection, which includes approximately 2,000,000 sentence pairs, can be used to train and test machine translation systems. Our test collection also includes search topics for cross-lingual patent retrieval and the contribution of machine translation to a patent retrieval task can also be evaluated. Our test collection will be available to the public for research purposes after the NTCIR final meeting.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/458_paper.pdf
Markdown (Informal)
[Producing a Test Collection for Patent Machine Translation in the Seventh NTCIR Workshop](http://www.lrec-conf.org/proceedings/lrec2008/pdf/458_paper.pdf) (Fujii et al., LREC 2008)
ACL