@inproceedings{sevcikova-zabokrtsky-2014-word,
title = "Word-Formation Network for {C}zech",
author = "{\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Magda and
{\v{Z}}abokrtsk{\'y}, Zden{\v{e}}k",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/501_Paper.pdf",
pages = "1087--1093",
abstract = "In the present paper, we describe the development of the lexical network DeriNet, which captures core word-formation relations on the set of around 266 thousand Czech lexemes. The network is currently limited to derivational relations because derivation is the most frequent and most productive word-formation process in Czech. This limitation is reflected in the architecture of the network: each lexeme is allowed to be linked up with just a single base word; composition as well as combined processes (composition with derivation) are thus not included. After a brief summarization of theoretical descriptions of Czech derivation and the state of the art of NLP approaches to Czech derivation, we discuss the linguistic background of the network and introduce the formal structure of the network and the semi-automatic annotation procedure. The network was initialized with a set of lexemes whose existence was supported by corpus evidence. Derivational links were created using three sources of information: links delivered by a tool for morphological analysis, links based on an automatically discovered set of derivation rules, and on a grammar-based set of rules. Finally, we propose some research topics which could profit from the existence of such lexical network.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sevcikova-zabokrtsky-2014-word">
<titleInfo>
<title>Word-Formation Network for Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Magda</namePart>
<namePart type="family">Ševčíková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdeněk</namePart>
<namePart type="family">Žabokrtský</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the present paper, we describe the development of the lexical network DeriNet, which captures core word-formation relations on the set of around 266 thousand Czech lexemes. The network is currently limited to derivational relations because derivation is the most frequent and most productive word-formation process in Czech. This limitation is reflected in the architecture of the network: each lexeme is allowed to be linked up with just a single base word; composition as well as combined processes (composition with derivation) are thus not included. After a brief summarization of theoretical descriptions of Czech derivation and the state of the art of NLP approaches to Czech derivation, we discuss the linguistic background of the network and introduce the formal structure of the network and the semi-automatic annotation procedure. The network was initialized with a set of lexemes whose existence was supported by corpus evidence. Derivational links were created using three sources of information: links delivered by a tool for morphological analysis, links based on an automatically discovered set of derivation rules, and on a grammar-based set of rules. Finally, we propose some research topics which could profit from the existence of such lexical network.</abstract>
<identifier type="citekey">sevcikova-zabokrtsky-2014-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/501_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1087</start>
<end>1093</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word-Formation Network for Czech
%A Ševčíková, Magda
%A Žabokrtský, Zdeněk
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F sevcikova-zabokrtsky-2014-word
%X In the present paper, we describe the development of the lexical network DeriNet, which captures core word-formation relations on the set of around 266 thousand Czech lexemes. The network is currently limited to derivational relations because derivation is the most frequent and most productive word-formation process in Czech. This limitation is reflected in the architecture of the network: each lexeme is allowed to be linked up with just a single base word; composition as well as combined processes (composition with derivation) are thus not included. After a brief summarization of theoretical descriptions of Czech derivation and the state of the art of NLP approaches to Czech derivation, we discuss the linguistic background of the network and introduce the formal structure of the network and the semi-automatic annotation procedure. The network was initialized with a set of lexemes whose existence was supported by corpus evidence. Derivational links were created using three sources of information: links delivered by a tool for morphological analysis, links based on an automatically discovered set of derivation rules, and on a grammar-based set of rules. Finally, we propose some research topics which could profit from the existence of such lexical network.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/501_Paper.pdf
%P 1087-1093
Markdown (Informal)
[Word-Formation Network for Czech](http://www.lrec-conf.org/proceedings/lrec2014/pdf/501_Paper.pdf) (Ševčíková & Žabokrtský, LREC 2014)
ACL
- Magda Ševčíková and Zdeněk Žabokrtský. 2014. Word-Formation Network for Czech. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1087–1093, Reykjavik, Iceland. European Language Resources Association (ELRA).