@inproceedings{bojar-etal-2010-data,
title = "Data Issues in {E}nglish-to-{H}indi Machine Translation",
author = "Bojar, Ond{\v{r}}ej and
Stra{\v{n}}{\'a}k, Pavel and
Zeman, Daniel",
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/756_Paper.pdf",
abstract = "Statistical machine translation to morphologically richer languages is a challenging task and more so if the source and target languages differ in word order. Current state-of-the-art MT systems thus deliver mediocre results. Adding more parallel data often helps improve the results; if it doesn't, it may be caused by various problems such as different domains, bad alignment or noise in the new data. In this paper we evaluate the English-to-Hindi MT task from this data perspective. We discuss several available parallel data sources and provide cross-evaluation results on their combinations using two freely available statistical MT systems. We demonstrate various problems encountered in the data and describe automatic methods of data cleaning and normalization. We also show that the contents of two independently distributed data sets can unexpectedly overlap, which negatively affects translation quality. Together with the error analysis, we also present a new tool for viewing aligned corpora, which makes it easier to detect difficult parts in the data even for a developer not speaking the target language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bojar-etal-2010-data">
<titleInfo>
<title>Data Issues in English-to-Hindi Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Straňák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Zeman</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 to morphologically richer languages is a challenging task and more so if the source and target languages differ in word order. Current state-of-the-art MT systems thus deliver mediocre results. Adding more parallel data often helps improve the results; if it doesn’t, it may be caused by various problems such as different domains, bad alignment or noise in the new data. In this paper we evaluate the English-to-Hindi MT task from this data perspective. We discuss several available parallel data sources and provide cross-evaluation results on their combinations using two freely available statistical MT systems. We demonstrate various problems encountered in the data and describe automatic methods of data cleaning and normalization. We also show that the contents of two independently distributed data sets can unexpectedly overlap, which negatively affects translation quality. Together with the error analysis, we also present a new tool for viewing aligned corpora, which makes it easier to detect difficult parts in the data even for a developer not speaking the target language.</abstract>
<identifier type="citekey">bojar-etal-2010-data</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/756_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Issues in English-to-Hindi Machine Translation
%A Bojar, Ondřej
%A Straňák, Pavel
%A Zeman, Daniel
%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 bojar-etal-2010-data
%X Statistical machine translation to morphologically richer languages is a challenging task and more so if the source and target languages differ in word order. Current state-of-the-art MT systems thus deliver mediocre results. Adding more parallel data often helps improve the results; if it doesn’t, it may be caused by various problems such as different domains, bad alignment or noise in the new data. In this paper we evaluate the English-to-Hindi MT task from this data perspective. We discuss several available parallel data sources and provide cross-evaluation results on their combinations using two freely available statistical MT systems. We demonstrate various problems encountered in the data and describe automatic methods of data cleaning and normalization. We also show that the contents of two independently distributed data sets can unexpectedly overlap, which negatively affects translation quality. Together with the error analysis, we also present a new tool for viewing aligned corpora, which makes it easier to detect difficult parts in the data even for a developer not speaking the target language.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/756_Paper.pdf
Markdown (Informal)
[Data Issues in English-to-Hindi Machine Translation](http://www.lrec-conf.org/proceedings/lrec2010/pdf/756_Paper.pdf) (Bojar et al., LREC 2010)
ACL
- Ondřej Bojar, Pavel Straňák, and Daniel Zeman. 2010. Data Issues in English-to-Hindi Machine Translation. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).