@inproceedings{rebout-langlais-2014-iterative,
title = "An Iterative Approach for Mining Parallel Sentences in a Comparable Corpus",
author = "Rebout, Lise and
Langlais, Phillippe",
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/43_Paper.pdf",
pages = "648--655",
abstract = "We describe an approach for mining parallel sentences in a collection of documents in two languages. While several approaches have been proposed for doing so, our proposal differs in several respects. First, we use a document level classifier in order to focus on potentially fruitful document pairs, an understudied approach. We show that mining less, but more parallel documents can lead to better gains in machine translation. Second, we compare different strategies for post-processing the output of a classifier trained to recognize parallel sentences. Last, we report a simple bootstrapping experiment which shows that promising sentence pairs extracted in a first stage can help to mine new sentence pairs in a second stage. We applied our approach on the English-French Wikipedia. Gains of a statistical machine translation (SMT) engine are analyzed along different test sets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rebout-langlais-2014-iterative">
<titleInfo>
<title>An Iterative Approach for Mining Parallel Sentences in a Comparable Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lise</namePart>
<namePart type="family">Rebout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillippe</namePart>
<namePart type="family">Langlais</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>We describe an approach for mining parallel sentences in a collection of documents in two languages. While several approaches have been proposed for doing so, our proposal differs in several respects. First, we use a document level classifier in order to focus on potentially fruitful document pairs, an understudied approach. We show that mining less, but more parallel documents can lead to better gains in machine translation. Second, we compare different strategies for post-processing the output of a classifier trained to recognize parallel sentences. Last, we report a simple bootstrapping experiment which shows that promising sentence pairs extracted in a first stage can help to mine new sentence pairs in a second stage. We applied our approach on the English-French Wikipedia. Gains of a statistical machine translation (SMT) engine are analyzed along different test sets.</abstract>
<identifier type="citekey">rebout-langlais-2014-iterative</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/43_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>648</start>
<end>655</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Iterative Approach for Mining Parallel Sentences in a Comparable Corpus
%A Rebout, Lise
%A Langlais, Phillippe
%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 rebout-langlais-2014-iterative
%X We describe an approach for mining parallel sentences in a collection of documents in two languages. While several approaches have been proposed for doing so, our proposal differs in several respects. First, we use a document level classifier in order to focus on potentially fruitful document pairs, an understudied approach. We show that mining less, but more parallel documents can lead to better gains in machine translation. Second, we compare different strategies for post-processing the output of a classifier trained to recognize parallel sentences. Last, we report a simple bootstrapping experiment which shows that promising sentence pairs extracted in a first stage can help to mine new sentence pairs in a second stage. We applied our approach on the English-French Wikipedia. Gains of a statistical machine translation (SMT) engine are analyzed along different test sets.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/43_Paper.pdf
%P 648-655
Markdown (Informal)
[An Iterative Approach for Mining Parallel Sentences in a Comparable Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/43_Paper.pdf) (Rebout & Langlais, LREC 2014)
ACL