@inproceedings{allauzen-bonneau-maynard-2008-training,
title = "Training and Evaluation of {POS} Taggers on the {F}rench {MULTITAG} Corpus",
author = "Allauzen, Alexandre and
Bonneau-Maynard, H{\'e}l{\`e}ne",
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/856_paper.pdf",
abstract = "The explicit introduction of morphosyntactic information into statistical machine translation approaches is receiving an important focus of attention. The current freely available Part of Speech (POS) taggers for the French language are based on a limited tagset which does not account for some flectional particularities. Moreover, there is a lack of a unified framework of training and evaluation for these kinds of linguistic resources. Therefore in this paper, three standard POS taggers (Treetagger, Brills tagger and the standard HMM POS tagger) are trained and evaluated in the same conditions on the French MULTITAG corpus. This POS-tagged corpus provides a tagset richer than the usual ones, including gender and number distinctions, for example. Experimental results show significant differences of performance between the taggers. According to the tagging accuracy estimated with a tagset of 300 items, taggers may be ranked as follows: Treetagger (95.7{\%}), Brills tagger (94.6{\%}), HMM tagger (93.4{\%}). Examples of translation outputs illustrate how considering gender and number distinctions in the POS tagset can be relevant.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="allauzen-bonneau-maynard-2008-training">
<titleInfo>
<title>Training and Evaluation of POS Taggers on the French MULTITAG Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Allauzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Bonneau-Maynard</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>The explicit introduction of morphosyntactic information into statistical machine translation approaches is receiving an important focus of attention. The current freely available Part of Speech (POS) taggers for the French language are based on a limited tagset which does not account for some flectional particularities. Moreover, there is a lack of a unified framework of training and evaluation for these kinds of linguistic resources. Therefore in this paper, three standard POS taggers (Treetagger, Brills tagger and the standard HMM POS tagger) are trained and evaluated in the same conditions on the French MULTITAG corpus. This POS-tagged corpus provides a tagset richer than the usual ones, including gender and number distinctions, for example. Experimental results show significant differences of performance between the taggers. According to the tagging accuracy estimated with a tagset of 300 items, taggers may be ranked as follows: Treetagger (95.7%), Brills tagger (94.6%), HMM tagger (93.4%). Examples of translation outputs illustrate how considering gender and number distinctions in the POS tagset can be relevant.</abstract>
<identifier type="citekey">allauzen-bonneau-maynard-2008-training</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/856_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training and Evaluation of POS Taggers on the French MULTITAG Corpus
%A Allauzen, Alexandre
%A Bonneau-Maynard, Hélène
%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 allauzen-bonneau-maynard-2008-training
%X The explicit introduction of morphosyntactic information into statistical machine translation approaches is receiving an important focus of attention. The current freely available Part of Speech (POS) taggers for the French language are based on a limited tagset which does not account for some flectional particularities. Moreover, there is a lack of a unified framework of training and evaluation for these kinds of linguistic resources. Therefore in this paper, three standard POS taggers (Treetagger, Brills tagger and the standard HMM POS tagger) are trained and evaluated in the same conditions on the French MULTITAG corpus. This POS-tagged corpus provides a tagset richer than the usual ones, including gender and number distinctions, for example. Experimental results show significant differences of performance between the taggers. According to the tagging accuracy estimated with a tagset of 300 items, taggers may be ranked as follows: Treetagger (95.7%), Brills tagger (94.6%), HMM tagger (93.4%). Examples of translation outputs illustrate how considering gender and number distinctions in the POS tagset can be relevant.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/856_paper.pdf
Markdown (Informal)
[Training and Evaluation of POS Taggers on the French MULTITAG Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/856_paper.pdf) (Allauzen & Bonneau-Maynard, LREC 2008)
ACL