@inproceedings{iliev-genov-2012-expanding,
title = "Expanding Parallel Resources for Medium-Density Languages for Free",
author = "Iliev, Georgi and
Genov, Angel",
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/743_Paper.pdf",
pages = "3937--3943",
abstract = "We discuss a previously proposed method for augmenting parallel corpora of limited size for the purposes of machine translation through monolingual paraphrasing of the source language. We develop a three-stage shallow paraphrasing procedure to be applied to the Swedish-Bulgarian language pair for which limited parallel resources exist. The source language exhibits specifics not typical of high-density languages already studied in a similar setting. Paraphrases of a highly productive type of compound nouns in Swedish are generated by a corpus-based technique. Certain Swedish noun-phrase types are paraphrased using basic heuristics. Further we introduce noun-phrase morphological variations for better wordform coverage. We evaluate the performance of a phrase-based statistical machine translation system trained on a baseline parallel corpus and on three stages of artificial enlargement of the source-language training data. Paraphrasing is shown to have no effect on performance for the Swedish-English translation task. We show a small, yet consistent, increase in the BLEU score of Swedish-Bulgarian translations of larger token spans on the first enlargement stage. A small improvement in the overall BLEU score of Swedish-Bulgarian translation is achieved on the second enlargement stage. We find that both improvements justify further research into the method for the Swedish-Bulgarian translation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iliev-genov-2012-expanding">
<titleInfo>
<title>Expanding Parallel Resources for Medium-Density Languages for Free</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georgi</namePart>
<namePart type="family">Iliev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="family">Genov</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>We discuss a previously proposed method for augmenting parallel corpora of limited size for the purposes of machine translation through monolingual paraphrasing of the source language. We develop a three-stage shallow paraphrasing procedure to be applied to the Swedish-Bulgarian language pair for which limited parallel resources exist. The source language exhibits specifics not typical of high-density languages already studied in a similar setting. Paraphrases of a highly productive type of compound nouns in Swedish are generated by a corpus-based technique. Certain Swedish noun-phrase types are paraphrased using basic heuristics. Further we introduce noun-phrase morphological variations for better wordform coverage. We evaluate the performance of a phrase-based statistical machine translation system trained on a baseline parallel corpus and on three stages of artificial enlargement of the source-language training data. Paraphrasing is shown to have no effect on performance for the Swedish-English translation task. We show a small, yet consistent, increase in the BLEU score of Swedish-Bulgarian translations of larger token spans on the first enlargement stage. A small improvement in the overall BLEU score of Swedish-Bulgarian translation is achieved on the second enlargement stage. We find that both improvements justify further research into the method for the Swedish-Bulgarian translation task.</abstract>
<identifier type="citekey">iliev-genov-2012-expanding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/743_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3937</start>
<end>3943</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Expanding Parallel Resources for Medium-Density Languages for Free
%A Iliev, Georgi
%A Genov, Angel
%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 iliev-genov-2012-expanding
%X We discuss a previously proposed method for augmenting parallel corpora of limited size for the purposes of machine translation through monolingual paraphrasing of the source language. We develop a three-stage shallow paraphrasing procedure to be applied to the Swedish-Bulgarian language pair for which limited parallel resources exist. The source language exhibits specifics not typical of high-density languages already studied in a similar setting. Paraphrases of a highly productive type of compound nouns in Swedish are generated by a corpus-based technique. Certain Swedish noun-phrase types are paraphrased using basic heuristics. Further we introduce noun-phrase morphological variations for better wordform coverage. We evaluate the performance of a phrase-based statistical machine translation system trained on a baseline parallel corpus and on three stages of artificial enlargement of the source-language training data. Paraphrasing is shown to have no effect on performance for the Swedish-English translation task. We show a small, yet consistent, increase in the BLEU score of Swedish-Bulgarian translations of larger token spans on the first enlargement stage. A small improvement in the overall BLEU score of Swedish-Bulgarian translation is achieved on the second enlargement stage. We find that both improvements justify further research into the method for the Swedish-Bulgarian translation task.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/743_Paper.pdf
%P 3937-3943
Markdown (Informal)
[Expanding Parallel Resources for Medium-Density Languages for Free](http://www.lrec-conf.org/proceedings/lrec2012/pdf/743_Paper.pdf) (Iliev & Genov, LREC 2012)
ACL