@inproceedings{hughes-etal-2006-feature,
title = "Feature-based Encoding and Querying Language Resources with Character Semantics",
author = "Hughes, Baden and
Gibbon, Dafydd 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/493_pdf.pdf",
abstract = "In this paper we discuss the explicit representation of character features pertaining to written language resources, which we argue are critically necessary in the long term of archiving language data. Much focus on the creation of language resources and their associated preservation is at the level of the corpus itself; however it is generally accepted that long term interpretation of these language resources requires more than a best practice data format. In particular, where language resources are created in linguistic fieldwork, and especially for minority languages, the need for preservation not only of the resource itself, but of additional metadata which allows for the resource to be accurately interpreted in the future is becoming a topic of research in itself. In this paper we extend earlier work on semantically based character decomposition to include representation of character properties in a variety of models, and a mechanism for exploiting these properties through queries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hughes-etal-2006-feature">
<titleInfo>
<title>Feature-based Encoding and Querying Language Resources with Character Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baden</namePart>
<namePart type="family">Hughes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dafydd</namePart>
<namePart type="family">Gibbon</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>In this paper we discuss the explicit representation of character features pertaining to written language resources, which we argue are critically necessary in the long term of archiving language data. Much focus on the creation of language resources and their associated preservation is at the level of the corpus itself; however it is generally accepted that long term interpretation of these language resources requires more than a best practice data format. In particular, where language resources are created in linguistic fieldwork, and especially for minority languages, the need for preservation not only of the resource itself, but of additional metadata which allows for the resource to be accurately interpreted in the future is becoming a topic of research in itself. In this paper we extend earlier work on semantically based character decomposition to include representation of character properties in a variety of models, and a mechanism for exploiting these properties through queries.</abstract>
<identifier type="citekey">hughes-etal-2006-feature</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/493_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Feature-based Encoding and Querying Language Resources with Character Semantics
%A Hughes, Baden
%A Gibbon, Dafydd
%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 hughes-etal-2006-feature
%X In this paper we discuss the explicit representation of character features pertaining to written language resources, which we argue are critically necessary in the long term of archiving language data. Much focus on the creation of language resources and their associated preservation is at the level of the corpus itself; however it is generally accepted that long term interpretation of these language resources requires more than a best practice data format. In particular, where language resources are created in linguistic fieldwork, and especially for minority languages, the need for preservation not only of the resource itself, but of additional metadata which allows for the resource to be accurately interpreted in the future is becoming a topic of research in itself. In this paper we extend earlier work on semantically based character decomposition to include representation of character properties in a variety of models, and a mechanism for exploiting these properties through queries.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/493_pdf.pdf
Markdown (Informal)
[Feature-based Encoding and Querying Language Resources with Character Semantics](http://www.lrec-conf.org/proceedings/lrec2006/pdf/493_pdf.pdf) (Hughes et al., LREC 2006)
ACL