@inproceedings{przepiorkowski-etal-2010-recent,
title = "Recent Developments in the {N}ational {C}orpus of {P}olish",
author = "Przepi{\'o}rkowski, Adam and
G{\'o}rski, Rafa{\l} L. and
{\L}azi{\'n}ski, Marek and
P{\k{e}}zik, Piotr",
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/152_Paper.pdf",
abstract = "The aim of the paper is to present recent ― as of March 2010 ― developments in the construction of the National Corpus of Polish (NKJP). The NKJP project was launched at the very end of 2007 and it is aimed at compiling a large, linguistically annotated corpus of contemporary Polish by the end of 2010. Out of the total pool of 1 billion words of text data collected in the project, a 300 million word balanced corpus will be selected to match a set of predefined representativeness criteria. This present paper outlines a number of recent developments in the NKJP project, including: 1) the design of text encoding XML schemata for various levels of linguistic information, 2) a new tool for manual annotation at various levels, 3) numerous improvements in search tools. As the work on NKJP progresses, it becomes clear that this project serves as an important testbed for linguistic annotation and interoperability standards. We believe that our recent experiences will prove relevant to future large-scale language resource compilation efforts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="przepiorkowski-etal-2010-recent">
<titleInfo>
<title>Recent Developments in the National Corpus of Polish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Przepiórkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafał</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Górski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Łaziński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Pęzik</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>The aim of the paper is to present recent ― as of March 2010 ― developments in the construction of the National Corpus of Polish (NKJP). The NKJP project was launched at the very end of 2007 and it is aimed at compiling a large, linguistically annotated corpus of contemporary Polish by the end of 2010. Out of the total pool of 1 billion words of text data collected in the project, a 300 million word balanced corpus will be selected to match a set of predefined representativeness criteria. This present paper outlines a number of recent developments in the NKJP project, including: 1) the design of text encoding XML schemata for various levels of linguistic information, 2) a new tool for manual annotation at various levels, 3) numerous improvements in search tools. As the work on NKJP progresses, it becomes clear that this project serves as an important testbed for linguistic annotation and interoperability standards. We believe that our recent experiences will prove relevant to future large-scale language resource compilation efforts.</abstract>
<identifier type="citekey">przepiorkowski-etal-2010-recent</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/152_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recent Developments in the National Corpus of Polish
%A Przepiórkowski, Adam
%A Górski, Rafał L.
%A Łaziński, Marek
%A Pęzik, Piotr
%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 przepiorkowski-etal-2010-recent
%X The aim of the paper is to present recent ― as of March 2010 ― developments in the construction of the National Corpus of Polish (NKJP). The NKJP project was launched at the very end of 2007 and it is aimed at compiling a large, linguistically annotated corpus of contemporary Polish by the end of 2010. Out of the total pool of 1 billion words of text data collected in the project, a 300 million word balanced corpus will be selected to match a set of predefined representativeness criteria. This present paper outlines a number of recent developments in the NKJP project, including: 1) the design of text encoding XML schemata for various levels of linguistic information, 2) a new tool for manual annotation at various levels, 3) numerous improvements in search tools. As the work on NKJP progresses, it becomes clear that this project serves as an important testbed for linguistic annotation and interoperability standards. We believe that our recent experiences will prove relevant to future large-scale language resource compilation efforts.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/152_Paper.pdf
Markdown (Informal)
[Recent Developments in the National Corpus of Polish](http://www.lrec-conf.org/proceedings/lrec2010/pdf/152_Paper.pdf) (Przepiórkowski et al., LREC 2010)
ACL
- Adam Przepiórkowski, Rafał L. Górski, Marek Łaziński, and Piotr Pęzik. 2010. Recent Developments in the National Corpus of Polish. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).