@inproceedings{allauzen-etal-2010-limsi,
title = "{LIMSI} @ {IWSLT} 2010",
author = "Allauzen, Alexandre and
Crego, Josep M. and
El-Kahlout, {\.I}lknur Durgar and
Hai-Son, Le and
Wisniewski, Guillaume and
Yvon, Fran{\c{c}}ois",
booktitle = "Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign",
month = dec # " 2-3",
year = "2010",
address = "Paris, France",
url = "https://aclanthology.org/2010.iwslt-evaluation.13",
pages = "105--112",
abstract = "This paper describes LIMSI{'}s Statistical Machine Translation systems (SMT) for the IWSLT evaluation, where we participated in two tasks (Talk for English to French and BTEC for Turkish to English). For the Talk task, we studied an extension of our in-house n-code SMT system (the integration of a bilingual reordering model over generalized translation units), as well as the use of training data extracted from Wikipedia in order to adapt the target language model. For the BTEC task, we concentrated on pre-processing schemes on the Turkish side in order to reduce the morphological discrepancies with the English side. We also evaluated the use of two different continuous space language models for such a small size of training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="allauzen-etal-2010-limsi">
<titleInfo>
<title>LIMSI @ IWSLT 2010</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Allauzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Crego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">İlknur</namePart>
<namePart type="given">Durgar</namePart>
<namePart type="family">El-Kahlout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Hai-Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Wisniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-dec 2-3</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Paris, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes LIMSI’s Statistical Machine Translation systems (SMT) for the IWSLT evaluation, where we participated in two tasks (Talk for English to French and BTEC for Turkish to English). For the Talk task, we studied an extension of our in-house n-code SMT system (the integration of a bilingual reordering model over generalized translation units), as well as the use of training data extracted from Wikipedia in order to adapt the target language model. For the BTEC task, we concentrated on pre-processing schemes on the Turkish side in order to reduce the morphological discrepancies with the English side. We also evaluated the use of two different continuous space language models for such a small size of training data.</abstract>
<identifier type="citekey">allauzen-etal-2010-limsi</identifier>
<location>
<url>https://aclanthology.org/2010.iwslt-evaluation.13</url>
</location>
<part>
<date>2010-dec 2-3</date>
<extent unit="page">
<start>105</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LIMSI @ IWSLT 2010
%A Allauzen, Alexandre
%A Crego, Josep M.
%A El-Kahlout, İlknur Durgar
%A Hai-Son, Le
%A Wisniewski, Guillaume
%A Yvon, François
%S Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2010
%8 dec 2 3
%C Paris, France
%F allauzen-etal-2010-limsi
%X This paper describes LIMSI’s Statistical Machine Translation systems (SMT) for the IWSLT evaluation, where we participated in two tasks (Talk for English to French and BTEC for Turkish to English). For the Talk task, we studied an extension of our in-house n-code SMT system (the integration of a bilingual reordering model over generalized translation units), as well as the use of training data extracted from Wikipedia in order to adapt the target language model. For the BTEC task, we concentrated on pre-processing schemes on the Turkish side in order to reduce the morphological discrepancies with the English side. We also evaluated the use of two different continuous space language models for such a small size of training data.
%U https://aclanthology.org/2010.iwslt-evaluation.13
%P 105-112
Markdown (Informal)
[LIMSI @ IWSLT 2010](https://aclanthology.org/2010.iwslt-evaluation.13) (Allauzen et al., IWSLT 2010)
ACL
- Alexandre Allauzen, Josep M. Crego, İlknur Durgar El-Kahlout, Le Hai-Son, Guillaume Wisniewski, and François Yvon. 2010. LIMSI @ IWSLT 2010. In Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 105–112, Paris, France.