@inproceedings{tufis-etal-2008-unsupervised,
title = "Unsupervised Lexical Acquisition for Part of Speech Tagging",
author = "Tufi{\c{s}}, Dan and
Irimia, Elena and
Ion, Radu and
Ceau{\c{s}}u, Alexandru",
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/56_paper.pdf",
abstract = "It is known that POS tagging is not very accurate for unknown words (words which the POS tagger has not seen in the training corpora). Thus, a first step to improve the tagging accuracy would be to extend the coverage of the taggers learned lexicon. It turns out that, through the use of a simple procedure, one can extend this lexicon without using additional, hard to obtain, hand-validated training corpora. The basic idea consists of merely adding new words along with their (correct) POS tags to the lexicon and trying to estimate the lexical distribution of these words according to similar ambiguity classes already present in the lexicon. We present a method of automatically acquire high quality POS tagging lexicons based on morphologic analysis and generation. Currently, this procedure works on Romanian for which we have a required paradigmatic generation procedure but the architecture remains general in the sense that given the appropriate substitutes for the morphological generator and POS tagger, one should obtain similar results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufis-etal-2008-unsupervised">
<titleInfo>
<title>Unsupervised Lexical Acquisition for Part of Speech Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufiş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Irimia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Ion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandru</namePart>
<namePart type="family">Ceauşu</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>It is known that POS tagging is not very accurate for unknown words (words which the POS tagger has not seen in the training corpora). Thus, a first step to improve the tagging accuracy would be to extend the coverage of the taggers learned lexicon. It turns out that, through the use of a simple procedure, one can extend this lexicon without using additional, hard to obtain, hand-validated training corpora. The basic idea consists of merely adding new words along with their (correct) POS tags to the lexicon and trying to estimate the lexical distribution of these words according to similar ambiguity classes already present in the lexicon. We present a method of automatically acquire high quality POS tagging lexicons based on morphologic analysis and generation. Currently, this procedure works on Romanian for which we have a required paradigmatic generation procedure but the architecture remains general in the sense that given the appropriate substitutes for the morphological generator and POS tagger, one should obtain similar results.</abstract>
<identifier type="citekey">tufis-etal-2008-unsupervised</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/56_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Lexical Acquisition for Part of Speech Tagging
%A Tufiş, Dan
%A Irimia, Elena
%A Ion, Radu
%A Ceauşu, Alexandru
%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 tufis-etal-2008-unsupervised
%X It is known that POS tagging is not very accurate for unknown words (words which the POS tagger has not seen in the training corpora). Thus, a first step to improve the tagging accuracy would be to extend the coverage of the taggers learned lexicon. It turns out that, through the use of a simple procedure, one can extend this lexicon without using additional, hard to obtain, hand-validated training corpora. The basic idea consists of merely adding new words along with their (correct) POS tags to the lexicon and trying to estimate the lexical distribution of these words according to similar ambiguity classes already present in the lexicon. We present a method of automatically acquire high quality POS tagging lexicons based on morphologic analysis and generation. Currently, this procedure works on Romanian for which we have a required paradigmatic generation procedure but the architecture remains general in the sense that given the appropriate substitutes for the morphological generator and POS tagger, one should obtain similar results.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/56_paper.pdf
Markdown (Informal)
[Unsupervised Lexical Acquisition for Part of Speech Tagging](http://www.lrec-conf.org/proceedings/lrec2008/pdf/56_paper.pdf) (Tufiş et al., LREC 2008)
ACL