@inproceedings{tufis-dragomirescu-2004-tiered,
title = "Tiered Tagging Revisited",
author = "Tufis, Dan and
Dragomirescu, Liviu",
editor = "Lino, Maria Teresa and
Xavier, Maria Francisca and
Ferreira, F{\'a}tima and
Costa, Rute and
Silva, Raquel",
booktitle = "Proceedings of the Fourth International Conference on Language Resources and Evaluation ({LREC}{'}04)",
month = may,
year = "2004",
address = "Lisbon, Portugal",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2004/pdf/296.pdf",
abstract = "In this paper we describe a new baseline tagset induction algorithm, which unlike the one described in previous work is fully automatic and produces tagsets with better performance than before. The algorithm is an information lossless transformation of the MULTEXT-EAST compliant lexical tags (MSD) into a reduced tagset that can be mapped back on the lexicon tagset fully deterministic. From the baseline tagsets, a corpus linguist, expert in the language in case, may further reduce the tagsets taking into account language distributional properties. As any further reduction of the baseline tagsets assumes losing information, adequate recovering rules should be designed for ensuring the final tagging in terms of lexicon encoding. The algorithm is described in details and the generated baseline tagsets for Czech, English, Estonian, Hungarian, Romanian and Slovenean are evaluated. They are much smaller and systematically ensures better tagging accuracy than the corresponding MSDs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufis-dragomirescu-2004-tiered">
<titleInfo>
<title>Tiered Tagging Revisited</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liviu</namePart>
<namePart type="family">Dragomirescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2004-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Lino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Francisca</namePart>
<namePart type="family">Xavier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fátima</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rute</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Lisbon, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe a new baseline tagset induction algorithm, which unlike the one described in previous work is fully automatic and produces tagsets with better performance than before. The algorithm is an information lossless transformation of the MULTEXT-EAST compliant lexical tags (MSD) into a reduced tagset that can be mapped back on the lexicon tagset fully deterministic. From the baseline tagsets, a corpus linguist, expert in the language in case, may further reduce the tagsets taking into account language distributional properties. As any further reduction of the baseline tagsets assumes losing information, adequate recovering rules should be designed for ensuring the final tagging in terms of lexicon encoding. The algorithm is described in details and the generated baseline tagsets for Czech, English, Estonian, Hungarian, Romanian and Slovenean are evaluated. They are much smaller and systematically ensures better tagging accuracy than the corresponding MSDs.</abstract>
<identifier type="citekey">tufis-dragomirescu-2004-tiered</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/296.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tiered Tagging Revisited
%A Tufis, Dan
%A Dragomirescu, Liviu
%Y Lino, Maria Teresa
%Y Xavier, Maria Francisca
%Y Ferreira, Fátima
%Y Costa, Rute
%Y Silva, Raquel
%S Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)
%D 2004
%8 May
%I European Language Resources Association (ELRA)
%C Lisbon, Portugal
%F tufis-dragomirescu-2004-tiered
%X In this paper we describe a new baseline tagset induction algorithm, which unlike the one described in previous work is fully automatic and produces tagsets with better performance than before. The algorithm is an information lossless transformation of the MULTEXT-EAST compliant lexical tags (MSD) into a reduced tagset that can be mapped back on the lexicon tagset fully deterministic. From the baseline tagsets, a corpus linguist, expert in the language in case, may further reduce the tagsets taking into account language distributional properties. As any further reduction of the baseline tagsets assumes losing information, adequate recovering rules should be designed for ensuring the final tagging in terms of lexicon encoding. The algorithm is described in details and the generated baseline tagsets for Czech, English, Estonian, Hungarian, Romanian and Slovenean are evaluated. They are much smaller and systematically ensures better tagging accuracy than the corresponding MSDs.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/296.pdf
Markdown (Informal)
[Tiered Tagging Revisited](http://www.lrec-conf.org/proceedings/lrec2004/pdf/296.pdf) (Tufis & Dragomirescu, LREC 2004)
ACL
- Dan Tufis and Liviu Dragomirescu. 2004. Tiered Tagging Revisited. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA).