@inproceedings{dandapat-groves-2014-mtwatch,
title = "{MTW}atch: A Tool for the Analysis of Noisy Parallel Data",
author = "Dandapat, Sandipan and
Groves, Declan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/272_Paper.pdf",
pages = "41--45",
abstract = "State-of-the-art statistical machine translation (SMT) technique requires a good quality parallel data to build a translation model. The availability of large parallel corpora has rapidly increased over the past decade. However, often these newly developed parallel data contains contain significant noise. In this paper, we describe our approach for classifying good quality parallel sentence pairs from noisy parallel data. We use 10 different features within a Support Vector Machine (SVM)-based model for our classification task. We report a reasonably good classification accuracy and its positive effect on overall MT accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dandapat-groves-2014-mtwatch">
<titleInfo>
<title>MTWatch: A Tool for the Analysis of Noisy Parallel Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Dandapat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Declan</namePart>
<namePart type="family">Groves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>State-of-the-art statistical machine translation (SMT) technique requires a good quality parallel data to build a translation model. The availability of large parallel corpora has rapidly increased over the past decade. However, often these newly developed parallel data contains contain significant noise. In this paper, we describe our approach for classifying good quality parallel sentence pairs from noisy parallel data. We use 10 different features within a Support Vector Machine (SVM)-based model for our classification task. We report a reasonably good classification accuracy and its positive effect on overall MT accuracy.</abstract>
<identifier type="citekey">dandapat-groves-2014-mtwatch</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/272_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>41</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTWatch: A Tool for the Analysis of Noisy Parallel Data
%A Dandapat, Sandipan
%A Groves, Declan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F dandapat-groves-2014-mtwatch
%X State-of-the-art statistical machine translation (SMT) technique requires a good quality parallel data to build a translation model. The availability of large parallel corpora has rapidly increased over the past decade. However, often these newly developed parallel data contains contain significant noise. In this paper, we describe our approach for classifying good quality parallel sentence pairs from noisy parallel data. We use 10 different features within a Support Vector Machine (SVM)-based model for our classification task. We report a reasonably good classification accuracy and its positive effect on overall MT accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/272_Paper.pdf
%P 41-45
Markdown (Informal)
[MTWatch: A Tool for the Analysis of Noisy Parallel Data](http://www.lrec-conf.org/proceedings/lrec2014/pdf/272_Paper.pdf) (Dandapat & Groves, LREC 2014)
ACL
- Sandipan Dandapat and Declan Groves. 2014. MTWatch: A Tool for the Analysis of Noisy Parallel Data. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 41–45, Reykjavik, Iceland. European Language Resources Association (ELRA).