@inproceedings{de-sousa-trippel-2006-building,
title = "Building a historical corpus for Classical {P}ortuguese: some technological aspects",
author = "de Sousa, Maria Clara Paix{\~a}o and
Trippel, Thorsten",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/378_pdf.pdf",
abstract = "This paper describes the restructuring process of a large corpus of historical documents and the system architecture that is used for accessing it. The initial challenge of this process was to get the most out of existing material, normalizing the legacy markup and harvesting the inherent information using widely available standards. This resulted in a conceptual and technical restructuring of the formerly existing corpus. The development of the standardized markup and techniques allowed the inclusion of important new materials, such as original 16th and 17th century prints and manuscripts; and enlarged the potential user groups. On the technological side, we were grounded on the premise that open standards are the best way of making sure that the resources will be accessible even after years in an archive. This is a welcomed result in view of the additional consequence of the remodeled corpus concept: it serves as a repository for important historical documents, some of which had been preserved for 500 years in paper format. This very rich material can from now on be handled freely for linguistic research goals.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-sousa-trippel-2006-building">
<titleInfo>
<title>Building a historical corpus for Classical Portuguese: some technological aspects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Clara</namePart>
<namePart type="given">Paixão</namePart>
<namePart type="family">de Sousa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thorsten</namePart>
<namePart type="family">Trippel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the restructuring process of a large corpus of historical documents and the system architecture that is used for accessing it. The initial challenge of this process was to get the most out of existing material, normalizing the legacy markup and harvesting the inherent information using widely available standards. This resulted in a conceptual and technical restructuring of the formerly existing corpus. The development of the standardized markup and techniques allowed the inclusion of important new materials, such as original 16th and 17th century prints and manuscripts; and enlarged the potential user groups. On the technological side, we were grounded on the premise that open standards are the best way of making sure that the resources will be accessible even after years in an archive. This is a welcomed result in view of the additional consequence of the remodeled corpus concept: it serves as a repository for important historical documents, some of which had been preserved for 500 years in paper format. This very rich material can from now on be handled freely for linguistic research goals.</abstract>
<identifier type="citekey">de-sousa-trippel-2006-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/378_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a historical corpus for Classical Portuguese: some technological aspects
%A de Sousa, Maria Clara Paixão
%A Trippel, Thorsten
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F de-sousa-trippel-2006-building
%X This paper describes the restructuring process of a large corpus of historical documents and the system architecture that is used for accessing it. The initial challenge of this process was to get the most out of existing material, normalizing the legacy markup and harvesting the inherent information using widely available standards. This resulted in a conceptual and technical restructuring of the formerly existing corpus. The development of the standardized markup and techniques allowed the inclusion of important new materials, such as original 16th and 17th century prints and manuscripts; and enlarged the potential user groups. On the technological side, we were grounded on the premise that open standards are the best way of making sure that the resources will be accessible even after years in an archive. This is a welcomed result in view of the additional consequence of the remodeled corpus concept: it serves as a repository for important historical documents, some of which had been preserved for 500 years in paper format. This very rich material can from now on be handled freely for linguistic research goals.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/378_pdf.pdf
Markdown (Informal)
[Building a historical corpus for Classical Portuguese: some technological aspects](http://www.lrec-conf.org/proceedings/lrec2006/pdf/378_pdf.pdf) (de Sousa & Trippel, LREC 2006)
ACL