@inproceedings{zervanou-mcnaught-2004-domain,
title = "A Domain-Independent Approach to {IE} Rule Development",
author = "Zervanou, Kalliopi and
McNaught, John",
editor = "Lino, Maria Teresa and
Xavier, Maria Francisca and
Ferreira, F{\'a}tima and
Costa, Rute and
Silva, Raquel",
booktitle = "Proceedings of the Fourth International Conference on Language Resources and Evaluation ({LREC}{'}04)",
month = may,
year = "2004",
address = "Lisbon, Portugal",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2004/pdf/355.pdf",
abstract = "A key element for the extraction of information in a natural language document is a set of shallow text analysis rules, which are typically based on pre-defined linguistic patterns. Current Information Extraction research aims at the automatic or semi-automatic acquisition of these rules. Within this research framework, we consider in this paper the potential for acquiring generic extraction patterns. Our research is based on the hypothesis that, terms (the linguistic representation of concepts in a specialised domain) and Named Entities (the names of persons, organisations and dates of importance in the text) can together be considered as the basic semantic entities of textual information and can therefore be used as a basis for the conceptual representation of domain specific texts and the definition of what constitutes an information extraction template in linguistic terms. The extraction patterns discovered by this approach involve significant associations of these semantic entities with verbs and they can subsequently be translated into the grammar formalism of choice.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zervanou-mcnaught-2004-domain">
<titleInfo>
<title>A Domain-Independent Approach to IE Rule Development</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalliopi</namePart>
<namePart type="family">Zervanou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">McNaught</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2004-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Lino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Francisca</namePart>
<namePart type="family">Xavier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fátima</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rute</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Lisbon, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A key element for the extraction of information in a natural language document is a set of shallow text analysis rules, which are typically based on pre-defined linguistic patterns. Current Information Extraction research aims at the automatic or semi-automatic acquisition of these rules. Within this research framework, we consider in this paper the potential for acquiring generic extraction patterns. Our research is based on the hypothesis that, terms (the linguistic representation of concepts in a specialised domain) and Named Entities (the names of persons, organisations and dates of importance in the text) can together be considered as the basic semantic entities of textual information and can therefore be used as a basis for the conceptual representation of domain specific texts and the definition of what constitutes an information extraction template in linguistic terms. The extraction patterns discovered by this approach involve significant associations of these semantic entities with verbs and they can subsequently be translated into the grammar formalism of choice.</abstract>
<identifier type="citekey">zervanou-mcnaught-2004-domain</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/355.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Domain-Independent Approach to IE Rule Development
%A Zervanou, Kalliopi
%A McNaught, John
%Y Lino, Maria Teresa
%Y Xavier, Maria Francisca
%Y Ferreira, Fátima
%Y Costa, Rute
%Y Silva, Raquel
%S Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)
%D 2004
%8 May
%I European Language Resources Association (ELRA)
%C Lisbon, Portugal
%F zervanou-mcnaught-2004-domain
%X A key element for the extraction of information in a natural language document is a set of shallow text analysis rules, which are typically based on pre-defined linguistic patterns. Current Information Extraction research aims at the automatic or semi-automatic acquisition of these rules. Within this research framework, we consider in this paper the potential for acquiring generic extraction patterns. Our research is based on the hypothesis that, terms (the linguistic representation of concepts in a specialised domain) and Named Entities (the names of persons, organisations and dates of importance in the text) can together be considered as the basic semantic entities of textual information and can therefore be used as a basis for the conceptual representation of domain specific texts and the definition of what constitutes an information extraction template in linguistic terms. The extraction patterns discovered by this approach involve significant associations of these semantic entities with verbs and they can subsequently be translated into the grammar formalism of choice.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/355.pdf
Markdown (Informal)
[A Domain-Independent Approach to IE Rule Development](http://www.lrec-conf.org/proceedings/lrec2004/pdf/355.pdf) (Zervanou & McNaught, LREC 2004)
ACL
- Kalliopi Zervanou and John McNaught. 2004. A Domain-Independent Approach to IE Rule Development. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA).