@inproceedings{guzman-etal-2013-amara,
title = "The {AMARA} corpus: building resources for translating the web`s educational content",
author = "Guzman, Francisco and
Sajjad, Hassan and
Vogel, Stephan and
Abdelali, Ahmed",
editor = "Zhang, Joy Ying",
booktitle = "Proceedings of the 10th International Workshop on Spoken Language Translation: Papers",
month = dec # " 5-6",
year = "2013",
address = "Heidelberg, Germany",
url = "https://aclanthology.org/2013.iwslt-papers.2/",
abstract = "In this paper, we introduce a new parallel corpus of subtitles of educational videos: the AMARA corpus for online educational content. We crawl a multilingual collection community generated subtitles, and present the results of processing the Arabic{--}English portion of the data, which yields a parallel corpus of about 2.6M Arabic and 3.9M English words. We explore different approaches to align the segments, and extrinsically evaluate the resulting parallel corpus on the standard TED-talks tst-2010. We observe that the data can be successfully used for this task, and also observe an absolute improvement of 1.6 BLEU when it is used in combination with TED data. Finally, we analyze some of the specific challenges when translating the educational content."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guzman-etal-2013-amara">
<titleInfo>
<title>The AMARA corpus: building resources for translating the web‘s educational content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Vogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2013-dec 5-6</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th International Workshop on Spoken Language Translation: Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joy</namePart>
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Heidelberg, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce a new parallel corpus of subtitles of educational videos: the AMARA corpus for online educational content. We crawl a multilingual collection community generated subtitles, and present the results of processing the Arabic–English portion of the data, which yields a parallel corpus of about 2.6M Arabic and 3.9M English words. We explore different approaches to align the segments, and extrinsically evaluate the resulting parallel corpus on the standard TED-talks tst-2010. We observe that the data can be successfully used for this task, and also observe an absolute improvement of 1.6 BLEU when it is used in combination with TED data. Finally, we analyze some of the specific challenges when translating the educational content.</abstract>
<identifier type="citekey">guzman-etal-2013-amara</identifier>
<location>
<url>https://aclanthology.org/2013.iwslt-papers.2/</url>
</location>
<part>
<date>2013-dec 5-6</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The AMARA corpus: building resources for translating the web‘s educational content
%A Guzman, Francisco
%A Sajjad, Hassan
%A Vogel, Stephan
%A Abdelali, Ahmed
%Y Zhang, Joy Ying
%S Proceedings of the 10th International Workshop on Spoken Language Translation: Papers
%D 2013
%8 dec 5 6
%C Heidelberg, Germany
%F guzman-etal-2013-amara
%X In this paper, we introduce a new parallel corpus of subtitles of educational videos: the AMARA corpus for online educational content. We crawl a multilingual collection community generated subtitles, and present the results of processing the Arabic–English portion of the data, which yields a parallel corpus of about 2.6M Arabic and 3.9M English words. We explore different approaches to align the segments, and extrinsically evaluate the resulting parallel corpus on the standard TED-talks tst-2010. We observe that the data can be successfully used for this task, and also observe an absolute improvement of 1.6 BLEU when it is used in combination with TED data. Finally, we analyze some of the specific challenges when translating the educational content.
%U https://aclanthology.org/2013.iwslt-papers.2/
Markdown (Informal)
[The AMARA corpus: building resources for translating the web’s educational content](https://aclanthology.org/2013.iwslt-papers.2/) (Guzman et al., IWSLT 2013)
ACL