@inproceedings{ljubesic-etal-2008-generating,
title = "Generating a Morphological Lexicon of Organization Entity Names",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Lauc, Tomislava and
Boras, Damir",
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/716_paper.pdf",
abstract = "This paper describes methods used for generating a morphological lexicon of organization entity names in Croatian. This resource is intended for two primary tasks: template-based natural language generation and named entity identification. The main problems concerning the lexicon generation are high level of inflection in Croatian and low linguistic quality of the primary resource containing named entities in normal form. The problem is divided into two subproblems concerning single-word and multi-word expressions. The single-word problem is solved by training a supervised learning algorithm called linear successive abstraction. With existing common language morphological resources and two simple hand-crafted rules backing up the algorithm, accuracy of 98.70{\%} on the test set is achieved. The multi-word problem is solved through a semi-automated process for multi-word entities occurring in the first 10,000 named entities. The generated multi-word lexicon will be used for natural language generation only while named entity identification will be solved algorithmically in forthcoming research. The single-word lexicon is capable of handling both tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2008-generating">
<titleInfo>
<title>Generating a Morphological Lexicon of Organization Entity Names</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomislava</namePart>
<namePart type="family">Lauc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damir</namePart>
<namePart type="family">Boras</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 describes methods used for generating a morphological lexicon of organization entity names in Croatian. This resource is intended for two primary tasks: template-based natural language generation and named entity identification. The main problems concerning the lexicon generation are high level of inflection in Croatian and low linguistic quality of the primary resource containing named entities in normal form. The problem is divided into two subproblems concerning single-word and multi-word expressions. The single-word problem is solved by training a supervised learning algorithm called linear successive abstraction. With existing common language morphological resources and two simple hand-crafted rules backing up the algorithm, accuracy of 98.70% on the test set is achieved. The multi-word problem is solved through a semi-automated process for multi-word entities occurring in the first 10,000 named entities. The generated multi-word lexicon will be used for natural language generation only while named entity identification will be solved algorithmically in forthcoming research. The single-word lexicon is capable of handling both tasks.</abstract>
<identifier type="citekey">ljubesic-etal-2008-generating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/716_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating a Morphological Lexicon of Organization Entity Names
%A Ljubešić, Nikola
%A Lauc, Tomislava
%A Boras, Damir
%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 ljubesic-etal-2008-generating
%X This paper describes methods used for generating a morphological lexicon of organization entity names in Croatian. This resource is intended for two primary tasks: template-based natural language generation and named entity identification. The main problems concerning the lexicon generation are high level of inflection in Croatian and low linguistic quality of the primary resource containing named entities in normal form. The problem is divided into two subproblems concerning single-word and multi-word expressions. The single-word problem is solved by training a supervised learning algorithm called linear successive abstraction. With existing common language morphological resources and two simple hand-crafted rules backing up the algorithm, accuracy of 98.70% on the test set is achieved. The multi-word problem is solved through a semi-automated process for multi-word entities occurring in the first 10,000 named entities. The generated multi-word lexicon will be used for natural language generation only while named entity identification will be solved algorithmically in forthcoming research. The single-word lexicon is capable of handling both tasks.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/716_paper.pdf
Markdown (Informal)
[Generating a Morphological Lexicon of Organization Entity Names](http://www.lrec-conf.org/proceedings/lrec2008/pdf/716_paper.pdf) (Ljubešić et al., LREC 2008)
ACL