@inproceedings{zhang-etal-2008-word,
title = "Word Alignment Annotation in a {J}apanese-{C}hinese Parallel Corpus",
author = "Zhang, Yujie and
Wang, Zhulong and
Uchimoto, Kiyotaka and
Ma, Qing and
Isahara, Hitoshi",
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/259_paper.pdf",
abstract = "Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual annotation of word {\&} phrase alignment is of significance to provide gold-standard for developing and evaluating both example-based machine translation model and statistical machine translation model. This paper presents the work of word {\&} phrase alignment annotation in the NICT Japanese-Chinese parallel corpus, which is constructed at the National Institute of Information and Communications Technology (NICT). We describe the specification of word alignment annotation and the tools specially developed for the manual annotation. The manual annotation on 17,000 sentence pairs has been completed. We examined the manually annotated word alignment data and extracted translation knowledge from the word {\&} phrase aligned corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2008-word">
<titleInfo>
<title>Word Alignment Annotation in a Japanese-Chinese Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yujie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhulong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyotaka</namePart>
<namePart type="family">Uchimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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>Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual annotation of word & phrase alignment is of significance to provide gold-standard for developing and evaluating both example-based machine translation model and statistical machine translation model. This paper presents the work of word & phrase alignment annotation in the NICT Japanese-Chinese parallel corpus, which is constructed at the National Institute of Information and Communications Technology (NICT). We describe the specification of word alignment annotation and the tools specially developed for the manual annotation. The manual annotation on 17,000 sentence pairs has been completed. We examined the manually annotated word alignment data and extracted translation knowledge from the word & phrase aligned corpus.</abstract>
<identifier type="citekey">zhang-etal-2008-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/259_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Alignment Annotation in a Japanese-Chinese Parallel Corpus
%A Zhang, Yujie
%A Wang, Zhulong
%A Uchimoto, Kiyotaka
%A Ma, Qing
%A Isahara, Hitoshi
%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 zhang-etal-2008-word
%X Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual annotation of word & phrase alignment is of significance to provide gold-standard for developing and evaluating both example-based machine translation model and statistical machine translation model. This paper presents the work of word & phrase alignment annotation in the NICT Japanese-Chinese parallel corpus, which is constructed at the National Institute of Information and Communications Technology (NICT). We describe the specification of word alignment annotation and the tools specially developed for the manual annotation. The manual annotation on 17,000 sentence pairs has been completed. We examined the manually annotated word alignment data and extracted translation knowledge from the word & phrase aligned corpus.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/259_paper.pdf
Markdown (Informal)
[Word Alignment Annotation in a Japanese-Chinese Parallel Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/259_paper.pdf) (Zhang et al., LREC 2008)
ACL
- Yujie Zhang, Zhulong Wang, Kiyotaka Uchimoto, Qing Ma, and Hitoshi Isahara. 2008. Word Alignment Annotation in a Japanese-Chinese Parallel Corpus. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).