@inproceedings{tufis-2014-large,
title = "Large {SMT} data-sets extracted from {W}ikipedia",
author = "Tufi{\c{s}}, Dan",
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/103_Paper.pdf",
pages = "656--663",
abstract = "The article presents experiments on mining Wikipedia for extracting SMT useful sentence pairs in three language pairs. Each extracted sentence pair is associated with a cross-lingual lexical similarity score based on which, several evaluations have been conducted to estimate the similarity thresholds which allow the extraction of the most useful data for training three-language pairs SMT systems. The experiments showed that for a similarity score higher than 0.7 all sentence pairs in the three language pairs were fully parallel. However, including in the training sets less parallel sentence pairs (that is with a lower similarity score) showed significant improvements in the translation quality (BLEU-based evaluations). The optimized SMT systems were evaluated on unseen test-sets also extracted from Wikipedia. As one of the main goals of our work was to help Wikipedia contributors to translate (with as little post editing as possible) new articles from major languages into less resourced languages and vice-versa, we call this type of translation experiments in-genre translation. As in the case of in-domain translation, our evaluations showed that using only in-genre training data for translating same genre new texts is better than mixing the training data with out-of-genre (even) parallel texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufis-2014-large">
<titleInfo>
<title>Large SMT data-sets extracted from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufiş</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>The article presents experiments on mining Wikipedia for extracting SMT useful sentence pairs in three language pairs. Each extracted sentence pair is associated with a cross-lingual lexical similarity score based on which, several evaluations have been conducted to estimate the similarity thresholds which allow the extraction of the most useful data for training three-language pairs SMT systems. The experiments showed that for a similarity score higher than 0.7 all sentence pairs in the three language pairs were fully parallel. However, including in the training sets less parallel sentence pairs (that is with a lower similarity score) showed significant improvements in the translation quality (BLEU-based evaluations). The optimized SMT systems were evaluated on unseen test-sets also extracted from Wikipedia. As one of the main goals of our work was to help Wikipedia contributors to translate (with as little post editing as possible) new articles from major languages into less resourced languages and vice-versa, we call this type of translation experiments in-genre translation. As in the case of in-domain translation, our evaluations showed that using only in-genre training data for translating same genre new texts is better than mixing the training data with out-of-genre (even) parallel texts.</abstract>
<identifier type="citekey">tufis-2014-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/103_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>656</start>
<end>663</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large SMT data-sets extracted from Wikipedia
%A Tufiş, Dan
%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 tufis-2014-large
%X The article presents experiments on mining Wikipedia for extracting SMT useful sentence pairs in three language pairs. Each extracted sentence pair is associated with a cross-lingual lexical similarity score based on which, several evaluations have been conducted to estimate the similarity thresholds which allow the extraction of the most useful data for training three-language pairs SMT systems. The experiments showed that for a similarity score higher than 0.7 all sentence pairs in the three language pairs were fully parallel. However, including in the training sets less parallel sentence pairs (that is with a lower similarity score) showed significant improvements in the translation quality (BLEU-based evaluations). The optimized SMT systems were evaluated on unseen test-sets also extracted from Wikipedia. As one of the main goals of our work was to help Wikipedia contributors to translate (with as little post editing as possible) new articles from major languages into less resourced languages and vice-versa, we call this type of translation experiments in-genre translation. As in the case of in-domain translation, our evaluations showed that using only in-genre training data for translating same genre new texts is better than mixing the training data with out-of-genre (even) parallel texts.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/103_Paper.pdf
%P 656-663
Markdown (Informal)
[Large SMT data-sets extracted from Wikipedia](http://www.lrec-conf.org/proceedings/lrec2014/pdf/103_Paper.pdf) (Tufiş, LREC 2014)
ACL
- Dan Tufiş. 2014. Large SMT data-sets extracted from Wikipedia. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 656–663, Reykjavik, Iceland. European Language Resources Association (ELRA).