@inproceedings{okita-2012-annotated,
title = "Annotated Corpora for Word Alignment between {J}apanese and {E}nglish and its Evaluation with {MAP}-based Word Aligner",
author = "Okita, Tsuyoshi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1109_Paper.pdf",
pages = "3241--3248",
abstract = "This paper presents two annotated corpora for word alignment between Japanese and English. We annotated on top of the IWSLT-2006 and the NTCIR-8 corpora. The IWSLT-2006 corpus is in the domain of travel conversation while the NTCIR-8 corpus is in the domain of patent. We annotated the first 500 sentence pairs from the IWSLT-2006 corpus and the first 100 sentence pairs from the NTCIR-8 corpus. After mentioned the annotation guideline, we present two evaluation algorithms how to use such hand-annotated corpora: although one is a well-known algorithm for word alignment researchers, one is novel which intends to evaluate a MAP-based word aligner of Okita et al. (2010b).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="okita-2012-annotated">
<titleInfo>
<title>Annotated Corpora for Word Alignment between Japanese and English and its Evaluation with MAP-based Word Aligner</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsuyoshi</namePart>
<namePart type="family">Okita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents two annotated corpora for word alignment between Japanese and English. We annotated on top of the IWSLT-2006 and the NTCIR-8 corpora. The IWSLT-2006 corpus is in the domain of travel conversation while the NTCIR-8 corpus is in the domain of patent. We annotated the first 500 sentence pairs from the IWSLT-2006 corpus and the first 100 sentence pairs from the NTCIR-8 corpus. After mentioned the annotation guideline, we present two evaluation algorithms how to use such hand-annotated corpora: although one is a well-known algorithm for word alignment researchers, one is novel which intends to evaluate a MAP-based word aligner of Okita et al. (2010b).</abstract>
<identifier type="citekey">okita-2012-annotated</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1109_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3241</start>
<end>3248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotated Corpora for Word Alignment between Japanese and English and its Evaluation with MAP-based Word Aligner
%A Okita, Tsuyoshi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F okita-2012-annotated
%X This paper presents two annotated corpora for word alignment between Japanese and English. We annotated on top of the IWSLT-2006 and the NTCIR-8 corpora. The IWSLT-2006 corpus is in the domain of travel conversation while the NTCIR-8 corpus is in the domain of patent. We annotated the first 500 sentence pairs from the IWSLT-2006 corpus and the first 100 sentence pairs from the NTCIR-8 corpus. After mentioned the annotation guideline, we present two evaluation algorithms how to use such hand-annotated corpora: although one is a well-known algorithm for word alignment researchers, one is novel which intends to evaluate a MAP-based word aligner of Okita et al. (2010b).
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1109_Paper.pdf
%P 3241-3248
Markdown (Informal)
[Annotated Corpora for Word Alignment between Japanese and English and its Evaluation with MAP-based Word Aligner](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1109_Paper.pdf) (Okita, LREC 2012)
ACL