@inproceedings{song-etal-2012-linguistic,
title = "Linguistic Resources for Handwriting Recognition and Translation Evaluation",
author = "Song, Zhiyi and
Ismael, Safa and
Grimes, Stephen and
Doermann, David and
Strassel, Stephanie",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/785_Paper.pdf",
pages = "3951--3955",
abstract = "We describe efforts to create corpora to support development and evaluation of handwriting recognition and translation technology. LDC has developed a stable pipeline and infrastructures for collecting and annotating handwriting linguistic resources to support the evaluation of MADCAT and OpenHaRT. We collect and annotate handwritten samples of pre-processed Arabic and Chinese data that has been already translated in English that is used in the GALE program. To date, LDC has recruited more than 600 scribes and collected, annotated and released more than 225,000 handwriting images. Most linguistic resources created for these programs will be made available to the larger research community by publishing in LDC's catalog. The phase 1 MADCAT corpus is now available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2012-linguistic">
<titleInfo>
<title>Linguistic Resources for Handwriting Recognition and Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiyi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Safa</namePart>
<namePart type="family">Ismael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Grimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Doermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe efforts to create corpora to support development and evaluation of handwriting recognition and translation technology. LDC has developed a stable pipeline and infrastructures for collecting and annotating handwriting linguistic resources to support the evaluation of MADCAT and OpenHaRT. We collect and annotate handwritten samples of pre-processed Arabic and Chinese data that has been already translated in English that is used in the GALE program. To date, LDC has recruited more than 600 scribes and collected, annotated and released more than 225,000 handwriting images. Most linguistic resources created for these programs will be made available to the larger research community by publishing in LDC’s catalog. The phase 1 MADCAT corpus is now available.</abstract>
<identifier type="citekey">song-etal-2012-linguistic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/785_Paper.pdf</url>
</location>
<part>
<date>2012-may</date>
<extent unit="page">
<start>3951</start>
<end>3955</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Resources for Handwriting Recognition and Translation Evaluation
%A Song, Zhiyi
%A Ismael, Safa
%A Grimes, Stephen
%A Doermann, David
%A Strassel, Stephanie
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 may
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F song-etal-2012-linguistic
%X We describe efforts to create corpora to support development and evaluation of handwriting recognition and translation technology. LDC has developed a stable pipeline and infrastructures for collecting and annotating handwriting linguistic resources to support the evaluation of MADCAT and OpenHaRT. We collect and annotate handwritten samples of pre-processed Arabic and Chinese data that has been already translated in English that is used in the GALE program. To date, LDC has recruited more than 600 scribes and collected, annotated and released more than 225,000 handwriting images. Most linguistic resources created for these programs will be made available to the larger research community by publishing in LDC’s catalog. The phase 1 MADCAT corpus is now available.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/785_Paper.pdf
%P 3951-3955
Markdown (Informal)
[Linguistic Resources for Handwriting Recognition and Translation Evaluation](http://www.lrec-conf.org/proceedings/lrec2012/pdf/785_Paper.pdf) (Song et al., LREC 2012)
ACL