@inproceedings{kaji-etal-2010-using,
title = "Using Comparable Corpora to Adapt a Translation Model to Domains",
author = "Kaji, Hiroyuki and
Tsunakawa, Takashi and
Okada, Daisuke",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/443_Paper.pdf",
abstract = "Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains to which SMT is applicable, we created a method for estimating translation pseudo-probabilities from bilingual comparable corpora. The essence of our method is to calculate pairwise correlations between the words associated with a source-language word, presently restricted to a noun, and its translations; word translation pseudo-probabilities are calculated based on the assumption that the more associated words a translation is correlated with, the higher its translation probability. We also describe a method we created for calculating noun-sequence translation pseudo-probabilities based on occurrence frequencies of noun sequences and constituent-word translation pseudo-probabilities. Then, we present a framework for merging the translation pseudo-probabilities estimated from in-domain comparable corpora with a translation model learned from an out-of-domain parallel corpus. Experiments using Japanese and English comparable corpora of scientific paper abstracts and a Japanese-English parallel corpus of patent abstracts showed promising results; the BLEU score was improved to some degree by incorporating the pseudo-probabilities estimated from the in-domain comparable corpora. Future work includes an optimization of the parameters and an extension to estimate translation pseudo-probabilities for verbs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaji-etal-2010-using">
<titleInfo>
<title>Using Comparable Corpora to Adapt a Translation Model to Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Kaji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Tsunakawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Okada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains to which SMT is applicable, we created a method for estimating translation pseudo-probabilities from bilingual comparable corpora. The essence of our method is to calculate pairwise correlations between the words associated with a source-language word, presently restricted to a noun, and its translations; word translation pseudo-probabilities are calculated based on the assumption that the more associated words a translation is correlated with, the higher its translation probability. We also describe a method we created for calculating noun-sequence translation pseudo-probabilities based on occurrence frequencies of noun sequences and constituent-word translation pseudo-probabilities. Then, we present a framework for merging the translation pseudo-probabilities estimated from in-domain comparable corpora with a translation model learned from an out-of-domain parallel corpus. Experiments using Japanese and English comparable corpora of scientific paper abstracts and a Japanese-English parallel corpus of patent abstracts showed promising results; the BLEU score was improved to some degree by incorporating the pseudo-probabilities estimated from the in-domain comparable corpora. Future work includes an optimization of the parameters and an extension to estimate translation pseudo-probabilities for verbs.</abstract>
<identifier type="citekey">kaji-etal-2010-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/443_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Comparable Corpora to Adapt a Translation Model to Domains
%A Kaji, Hiroyuki
%A Tsunakawa, Takashi
%A Okada, Daisuke
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F kaji-etal-2010-using
%X Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains to which SMT is applicable, we created a method for estimating translation pseudo-probabilities from bilingual comparable corpora. The essence of our method is to calculate pairwise correlations between the words associated with a source-language word, presently restricted to a noun, and its translations; word translation pseudo-probabilities are calculated based on the assumption that the more associated words a translation is correlated with, the higher its translation probability. We also describe a method we created for calculating noun-sequence translation pseudo-probabilities based on occurrence frequencies of noun sequences and constituent-word translation pseudo-probabilities. Then, we present a framework for merging the translation pseudo-probabilities estimated from in-domain comparable corpora with a translation model learned from an out-of-domain parallel corpus. Experiments using Japanese and English comparable corpora of scientific paper abstracts and a Japanese-English parallel corpus of patent abstracts showed promising results; the BLEU score was improved to some degree by incorporating the pseudo-probabilities estimated from the in-domain comparable corpora. Future work includes an optimization of the parameters and an extension to estimate translation pseudo-probabilities for verbs.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/443_Paper.pdf
Markdown (Informal)
[Using Comparable Corpora to Adapt a Translation Model to Domains](http://www.lrec-conf.org/proceedings/lrec2010/pdf/443_Paper.pdf) (Kaji et al., LREC 2010)
ACL