@inproceedings{strassel-etal-2008-new,
title = "New Resources for Document Classification, Analysis and Translation Technologies",
author = "Strassel, Stephanie and
Friedman, Lauren and
Ismael, Safa and
Brandschain, Linda",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/772_paper.pdf",
abstract = "The goal of the DARPA MADCAT (Multilingual Automatic Document Classification Analysis and Translation) Program is to automatically convert foreign language text images into English transcripts, for use by humans and downstream applications. The first phase the program focuses on translation of handwritten Arabic documents. Linguistic Data Consortium (LDC) is creating publicly available linguistic resources for MADCAT technologies, on a scale and richness not previously available. Corpora will consist of existing LDC corpora and data donations from MADCAT partners, plus new data collection to provide high quality material for evaluation and to address strategic gaps (for genre, dialect, image quality, etc.) in the existing resources. Training and test data properties will expand over time to encompass a wide range of topics and genres: letters, diaries, training manuals, brochures, signs, ledgers, memos, instructions, postcards and forms among others. Data will be ground truthed, with line, word and token segmentation and zoning, and translations and word alignments will be produced for a subset. Evaluation data will be carefully selected from the available data pools and high quality references will be produced, which can be used to compare MADCAT system performance against the human-produced gold standard.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strassel-etal-2008-new">
<titleInfo>
<title>New Resources for Document Classification, Analysis and Translation Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauren</namePart>
<namePart type="family">Friedman</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">Linda</namePart>
<namePart type="family">Brandschain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The goal of the DARPA MADCAT (Multilingual Automatic Document Classification Analysis and Translation) Program is to automatically convert foreign language text images into English transcripts, for use by humans and downstream applications. The first phase the program focuses on translation of handwritten Arabic documents. Linguistic Data Consortium (LDC) is creating publicly available linguistic resources for MADCAT technologies, on a scale and richness not previously available. Corpora will consist of existing LDC corpora and data donations from MADCAT partners, plus new data collection to provide high quality material for evaluation and to address strategic gaps (for genre, dialect, image quality, etc.) in the existing resources. Training and test data properties will expand over time to encompass a wide range of topics and genres: letters, diaries, training manuals, brochures, signs, ledgers, memos, instructions, postcards and forms among others. Data will be ground truthed, with line, word and token segmentation and zoning, and translations and word alignments will be produced for a subset. Evaluation data will be carefully selected from the available data pools and high quality references will be produced, which can be used to compare MADCAT system performance against the human-produced gold standard.</abstract>
<identifier type="citekey">strassel-etal-2008-new</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/772_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New Resources for Document Classification, Analysis and Translation Technologies
%A Strassel, Stephanie
%A Friedman, Lauren
%A Ismael, Safa
%A Brandschain, Linda
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F strassel-etal-2008-new
%X The goal of the DARPA MADCAT (Multilingual Automatic Document Classification Analysis and Translation) Program is to automatically convert foreign language text images into English transcripts, for use by humans and downstream applications. The first phase the program focuses on translation of handwritten Arabic documents. Linguistic Data Consortium (LDC) is creating publicly available linguistic resources for MADCAT technologies, on a scale and richness not previously available. Corpora will consist of existing LDC corpora and data donations from MADCAT partners, plus new data collection to provide high quality material for evaluation and to address strategic gaps (for genre, dialect, image quality, etc.) in the existing resources. Training and test data properties will expand over time to encompass a wide range of topics and genres: letters, diaries, training manuals, brochures, signs, ledgers, memos, instructions, postcards and forms among others. Data will be ground truthed, with line, word and token segmentation and zoning, and translations and word alignments will be produced for a subset. Evaluation data will be carefully selected from the available data pools and high quality references will be produced, which can be used to compare MADCAT system performance against the human-produced gold standard.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/772_paper.pdf
Markdown (Informal)
[New Resources for Document Classification, Analysis and Translation Technologies](http://www.lrec-conf.org/proceedings/lrec2008/pdf/772_paper.pdf) (Strassel et al., LREC 2008)
ACL