@inproceedings{oostdijk-etal-2010-constructing,
title = "Constructing a Broad-coverage Lexicon for Text Mining in the Patent Domain",
author = "Oostdijk, Nelleke and
Verberne, Suzan and
Koster, Cornelis",
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/378_Paper.pdf",
abstract = "For mining intellectual property texts (patents), a broad-coverage lexicon that covers general English words together with terminology from the patent domain is indispensable. The patent domain is very diffuse as it comprises a variety of technical domains (e.g. Human Necessities, Chemistry {\&} Metallurgy and Physics in the International Patent Classification). As a result, collecting a lexicon that covers the language used in patent texts is not a straightforward task. In this paper we describe the approach that we have developed for the semi-automatic construction of a broad-coverage lexicon for classification and information retrieval in the patent domain and which combines information from multiple sources. Our contribution is twofold. First, we provide insight into the difficulties of developing lexical resources for information retrieval and text mining in the patent domain, a research and development field that is expanding quickly. Second, we create a broad coverage lexicon annotated with rich lexical information and containing both general English word forms and domain terminology for various technical domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oostdijk-etal-2010-constructing">
<titleInfo>
<title>Constructing a Broad-coverage Lexicon for Text Mining in the Patent Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nelleke</namePart>
<namePart type="family">Oostdijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzan</namePart>
<namePart type="family">Verberne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelis</namePart>
<namePart type="family">Koster</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>For mining intellectual property texts (patents), a broad-coverage lexicon that covers general English words together with terminology from the patent domain is indispensable. The patent domain is very diffuse as it comprises a variety of technical domains (e.g. Human Necessities, Chemistry & Metallurgy and Physics in the International Patent Classification). As a result, collecting a lexicon that covers the language used in patent texts is not a straightforward task. In this paper we describe the approach that we have developed for the semi-automatic construction of a broad-coverage lexicon for classification and information retrieval in the patent domain and which combines information from multiple sources. Our contribution is twofold. First, we provide insight into the difficulties of developing lexical resources for information retrieval and text mining in the patent domain, a research and development field that is expanding quickly. Second, we create a broad coverage lexicon annotated with rich lexical information and containing both general English word forms and domain terminology for various technical domains.</abstract>
<identifier type="citekey">oostdijk-etal-2010-constructing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/378_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing a Broad-coverage Lexicon for Text Mining in the Patent Domain
%A Oostdijk, Nelleke
%A Verberne, Suzan
%A Koster, Cornelis
%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 oostdijk-etal-2010-constructing
%X For mining intellectual property texts (patents), a broad-coverage lexicon that covers general English words together with terminology from the patent domain is indispensable. The patent domain is very diffuse as it comprises a variety of technical domains (e.g. Human Necessities, Chemistry & Metallurgy and Physics in the International Patent Classification). As a result, collecting a lexicon that covers the language used in patent texts is not a straightforward task. In this paper we describe the approach that we have developed for the semi-automatic construction of a broad-coverage lexicon for classification and information retrieval in the patent domain and which combines information from multiple sources. Our contribution is twofold. First, we provide insight into the difficulties of developing lexical resources for information retrieval and text mining in the patent domain, a research and development field that is expanding quickly. Second, we create a broad coverage lexicon annotated with rich lexical information and containing both general English word forms and domain terminology for various technical domains.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/378_Paper.pdf
Markdown (Informal)
[Constructing a Broad-coverage Lexicon for Text Mining in the Patent Domain](http://www.lrec-conf.org/proceedings/lrec2010/pdf/378_Paper.pdf) (Oostdijk et al., LREC 2010)
ACL