@inproceedings{newbold-gillam-2008-automatic,
title = "Automatic Document Quality Control",
author = "Newbold, Neil and
Gillam, Lee",
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/145_paper.pdf",
abstract = "This paper focuses on automatically improving the readability of documents. We explore mechanisms relating to content control that could be used (i) by authors to improve the quality and consistency of the language used in authoring; and (ii) to find a means to demonstrate this to readers. To achieve this, we implemented and evaluated a number of software components, including those of the University of Surrey Department of Computings content analysis applications (System Quirk). The software integrates these components within the commonly available GATE software and incorporates language resources considered useful within the standards development process: a Plain English thesaurus; lookup of ISO terminology provided from a terminology management system (TMS) via ISO 16642; automatic terminology discovery using statistical and linguistic techniques; and readability metrics. Results lead us to the development of an assistive tool, initially for authors of standards but not considered to be limited only to such authors, and also to a system that provides automatic annotation of texts to help readers to understand them. We describe the system developed and made freely available under the auspices of the EU eContent project LIRICS.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="newbold-gillam-2008-automatic">
<titleInfo>
<title>Automatic Document Quality Control</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neil</namePart>
<namePart type="family">Newbold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lee</namePart>
<namePart type="family">Gillam</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>This paper focuses on automatically improving the readability of documents. We explore mechanisms relating to content control that could be used (i) by authors to improve the quality and consistency of the language used in authoring; and (ii) to find a means to demonstrate this to readers. To achieve this, we implemented and evaluated a number of software components, including those of the University of Surrey Department of Computings content analysis applications (System Quirk). The software integrates these components within the commonly available GATE software and incorporates language resources considered useful within the standards development process: a Plain English thesaurus; lookup of ISO terminology provided from a terminology management system (TMS) via ISO 16642; automatic terminology discovery using statistical and linguistic techniques; and readability metrics. Results lead us to the development of an assistive tool, initially for authors of standards but not considered to be limited only to such authors, and also to a system that provides automatic annotation of texts to help readers to understand them. We describe the system developed and made freely available under the auspices of the EU eContent project LIRICS.</abstract>
<identifier type="citekey">newbold-gillam-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/145_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Document Quality Control
%A Newbold, Neil
%A Gillam, Lee
%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 newbold-gillam-2008-automatic
%X This paper focuses on automatically improving the readability of documents. We explore mechanisms relating to content control that could be used (i) by authors to improve the quality and consistency of the language used in authoring; and (ii) to find a means to demonstrate this to readers. To achieve this, we implemented and evaluated a number of software components, including those of the University of Surrey Department of Computings content analysis applications (System Quirk). The software integrates these components within the commonly available GATE software and incorporates language resources considered useful within the standards development process: a Plain English thesaurus; lookup of ISO terminology provided from a terminology management system (TMS) via ISO 16642; automatic terminology discovery using statistical and linguistic techniques; and readability metrics. Results lead us to the development of an assistive tool, initially for authors of standards but not considered to be limited only to such authors, and also to a system that provides automatic annotation of texts to help readers to understand them. We describe the system developed and made freely available under the auspices of the EU eContent project LIRICS.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/145_paper.pdf
Markdown (Informal)
[Automatic Document Quality Control](http://www.lrec-conf.org/proceedings/lrec2008/pdf/145_paper.pdf) (Newbold & Gillam, LREC 2008)
ACL
- Neil Newbold and Lee Gillam. 2008. Automatic Document Quality Control. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).