@inproceedings{willis-etal-2010-xml,
title = "From {XML} to {XML}: The Why and How of Making the Biodiversity Literature Accessible to Researchers",
author = "Willis, Alistair and
King, David and
Morse, David and
Dil, Anton and
Lyal, Chris and
Roberts, Dave",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/787_Paper.pdf",
abstract = "We present the ABLE document collection, which consists of a set of annotated volumes of the Bulletin of the British Museum (Natural History). These were developed during our ongoing work on automating the markup of scanned copies of the biodiversity literature. Such automation is required if historic literature is to be used to inform contemporary issues in biodiversity research. We consider an enhanced TEI XML markup language, which is used as an intermediate stage in translating from the initial XML obtained from Optical Character Recognition to taXMLit, the target annotation schema. The intermediate representation allows additional information from external sources such as a taxonomic thesaurus to be incorporated before the final translation into taXMLit. We give an overview of the project workflow in automating the markup process, and consider what extensions to existing markup schema will be required to best support working taxonomists. Finally, we discuss some of the particular issues which were encountered in converting between different XML formats.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="willis-etal-2010-xml">
<titleInfo>
<title>From XML to XML: The Why and How of Making the Biodiversity Literature Accessible to Researchers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Willis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Morse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Dil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Lyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dave</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the ABLE document collection, which consists of a set of annotated volumes of the Bulletin of the British Museum (Natural History). These were developed during our ongoing work on automating the markup of scanned copies of the biodiversity literature. Such automation is required if historic literature is to be used to inform contemporary issues in biodiversity research. We consider an enhanced TEI XML markup language, which is used as an intermediate stage in translating from the initial XML obtained from Optical Character Recognition to taXMLit, the target annotation schema. The intermediate representation allows additional information from external sources such as a taxonomic thesaurus to be incorporated before the final translation into taXMLit. We give an overview of the project workflow in automating the markup process, and consider what extensions to existing markup schema will be required to best support working taxonomists. Finally, we discuss some of the particular issues which were encountered in converting between different XML formats.</abstract>
<identifier type="citekey">willis-etal-2010-xml</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/787_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From XML to XML: The Why and How of Making the Biodiversity Literature Accessible to Researchers
%A Willis, Alistair
%A King, David
%A Morse, David
%A Dil, Anton
%A Lyal, Chris
%A Roberts, Dave
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F willis-etal-2010-xml
%X We present the ABLE document collection, which consists of a set of annotated volumes of the Bulletin of the British Museum (Natural History). These were developed during our ongoing work on automating the markup of scanned copies of the biodiversity literature. Such automation is required if historic literature is to be used to inform contemporary issues in biodiversity research. We consider an enhanced TEI XML markup language, which is used as an intermediate stage in translating from the initial XML obtained from Optical Character Recognition to taXMLit, the target annotation schema. The intermediate representation allows additional information from external sources such as a taxonomic thesaurus to be incorporated before the final translation into taXMLit. We give an overview of the project workflow in automating the markup process, and consider what extensions to existing markup schema will be required to best support working taxonomists. Finally, we discuss some of the particular issues which were encountered in converting between different XML formats.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/787_Paper.pdf
Markdown (Informal)
[From XML to XML: The Why and How of Making the Biodiversity Literature Accessible to Researchers](http://www.lrec-conf.org/proceedings/lrec2010/pdf/787_Paper.pdf) (Willis et al., LREC 2010)
ACL