@inproceedings{kobylinski-2014-polita,
title = "{P}oli{T}a: A multitagger for {P}olish",
author = "Kobyli{\'n}ski, {\L}ukasz",
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/1018_Paper.pdf",
pages = "2949--2954",
abstract = "Part-of-Speech (POS) tagging is a crucial task in Natural Language Processing (NLP). POS tags may be assigned to tokens in text manually, by trained linguists, or using algorithmic approaches. Particularly, in the case of annotated text corpora, the quantity of textual data makes it unfeasible to rely on manual tagging and automated methods are used extensively. The quality of such methods is of critical importance, as even 1{\%} tagger error rate results in introducing millions of errors in a corpus consisting of a billion tokens. In case of Polish several POS taggers have been proposed to date, but even the best of the taggers achieves an accuracy of ca. 93{\%}, as measured on the one million subcorpus of the National Corpus of Polish (NCP). As the task of tagging is an example of classification, in this article we introduce a new POS tagger for Polish, which is based on the idea of combining several classifiers to produce higher quality tagging results than using any of the taggers individually.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kobylinski-2014-polita">
<titleInfo>
<title>PoliTa: A multitagger for Polish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Kobyliński</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>Part-of-Speech (POS) tagging is a crucial task in Natural Language Processing (NLP). POS tags may be assigned to tokens in text manually, by trained linguists, or using algorithmic approaches. Particularly, in the case of annotated text corpora, the quantity of textual data makes it unfeasible to rely on manual tagging and automated methods are used extensively. The quality of such methods is of critical importance, as even 1% tagger error rate results in introducing millions of errors in a corpus consisting of a billion tokens. In case of Polish several POS taggers have been proposed to date, but even the best of the taggers achieves an accuracy of ca. 93%, as measured on the one million subcorpus of the National Corpus of Polish (NCP). As the task of tagging is an example of classification, in this article we introduce a new POS tagger for Polish, which is based on the idea of combining several classifiers to produce higher quality tagging results than using any of the taggers individually.</abstract>
<identifier type="citekey">kobylinski-2014-polita</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1018_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2949</start>
<end>2954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PoliTa: A multitagger for Polish
%A Kobyliński, Łukasz
%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 kobylinski-2014-polita
%X Part-of-Speech (POS) tagging is a crucial task in Natural Language Processing (NLP). POS tags may be assigned to tokens in text manually, by trained linguists, or using algorithmic approaches. Particularly, in the case of annotated text corpora, the quantity of textual data makes it unfeasible to rely on manual tagging and automated methods are used extensively. The quality of such methods is of critical importance, as even 1% tagger error rate results in introducing millions of errors in a corpus consisting of a billion tokens. In case of Polish several POS taggers have been proposed to date, but even the best of the taggers achieves an accuracy of ca. 93%, as measured on the one million subcorpus of the National Corpus of Polish (NCP). As the task of tagging is an example of classification, in this article we introduce a new POS tagger for Polish, which is based on the idea of combining several classifiers to produce higher quality tagging results than using any of the taggers individually.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1018_Paper.pdf
%P 2949-2954
Markdown (Informal)
[PoliTa: A multitagger for Polish](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1018_Paper.pdf) (Kobyliński, LREC 2014)
ACL
- Łukasz Kobyliński. 2014. PoliTa: A multitagger for Polish. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2949–2954, Reykjavik, Iceland. European Language Resources Association (ELRA).