@inproceedings{cakmak-etal-2012-word,
title = "Word Alignment for {E}nglish-{T}urkish Language Pair",
author = {{\c{C}}akmak, Mehmet Talha and
Acar, S{\"u}leyman and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en},
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/380_Paper.pdf",
pages = "2177--2180",
abstract = "Word alignment is an important step for machine translation systems. Although the alignment performance between grammatically similar languages is reported to be very high in many studies, the case is not the same for language pairs from different language families. In this study, we are focusing on English-Turkish language pairs. Turkish is a highly agglutinative language with a very productive and rich morphology whereas English has a very poor morphology when compared to this language. As a result of this, one Turkish word is usually aligned with several English words. The traditional models which use word-level alignment approaches generally fail in such circumstances. In this study, we evaluate a Giza++ system by splitting the words into their morphological units (stem and suffixes) and compare the model with the traditional one. For the first time, we evaluate the performance of our aligner on gold standard parallel sentences rather than in a real machine translation system. Our approach reduced the alignment error rate by 40{\%} relative. Finally, a new test corpus of 300 manually aligned sentences is released together with this study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cakmak-etal-2012-word">
<titleInfo>
<title>Word Alignment for English-Turkish Language Pair</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Talha</namePart>
<namePart type="family">Çakmak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Süleyman</namePart>
<namePart type="family">Acar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</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>Word alignment is an important step for machine translation systems. Although the alignment performance between grammatically similar languages is reported to be very high in many studies, the case is not the same for language pairs from different language families. In this study, we are focusing on English-Turkish language pairs. Turkish is a highly agglutinative language with a very productive and rich morphology whereas English has a very poor morphology when compared to this language. As a result of this, one Turkish word is usually aligned with several English words. The traditional models which use word-level alignment approaches generally fail in such circumstances. In this study, we evaluate a Giza++ system by splitting the words into their morphological units (stem and suffixes) and compare the model with the traditional one. For the first time, we evaluate the performance of our aligner on gold standard parallel sentences rather than in a real machine translation system. Our approach reduced the alignment error rate by 40% relative. Finally, a new test corpus of 300 manually aligned sentences is released together with this study.</abstract>
<identifier type="citekey">cakmak-etal-2012-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/380_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2177</start>
<end>2180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Alignment for English-Turkish Language Pair
%A Çakmak, Mehmet Talha
%A Acar, Süleyman
%A Eryiğit, Gülşen
%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 cakmak-etal-2012-word
%X Word alignment is an important step for machine translation systems. Although the alignment performance between grammatically similar languages is reported to be very high in many studies, the case is not the same for language pairs from different language families. In this study, we are focusing on English-Turkish language pairs. Turkish is a highly agglutinative language with a very productive and rich morphology whereas English has a very poor morphology when compared to this language. As a result of this, one Turkish word is usually aligned with several English words. The traditional models which use word-level alignment approaches generally fail in such circumstances. In this study, we evaluate a Giza++ system by splitting the words into their morphological units (stem and suffixes) and compare the model with the traditional one. For the first time, we evaluate the performance of our aligner on gold standard parallel sentences rather than in a real machine translation system. Our approach reduced the alignment error rate by 40% relative. Finally, a new test corpus of 300 manually aligned sentences is released together with this study.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/380_Paper.pdf
%P 2177-2180
Markdown (Informal)
[Word Alignment for English-Turkish Language Pair](http://www.lrec-conf.org/proceedings/lrec2012/pdf/380_Paper.pdf) (Çakmak et al., LREC 2012)
ACL
- Mehmet Talha Çakmak, Süleyman Acar, and Gülşen Eryiğit. 2012. Word Alignment for English-Turkish Language Pair. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2177–2180, Istanbul, Turkey. European Language Resources Association (ELRA).