@inproceedings{hulden-francom-2012-boosting,
title = "Boosting statistical tagger accuracy with simple rule-based grammars",
author = "Hulden, Mans and
Francom, Jerid",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1075_Paper.pdf",
pages = "2114--2117",
abstract = "We report on several experiments on combining a rule-based tagger and a trigram tagger for Spanish. The results show that one can boost the accuracy of the best performing n-gram taggers by quickly developing a rough rule-based grammar to complement the statistically induced one and then combining the output of the two. The specific method of combination is crucial for achieving good results. The method provides particularly large gains in accuracy when only a small amount of tagged data is available for training a HMM, as may be the case for lesser-resourced and minority languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hulden-francom-2012-boosting">
<titleInfo>
<title>Boosting statistical tagger accuracy with simple rule-based grammars</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mans</namePart>
<namePart type="family">Hulden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jerid</namePart>
<namePart type="family">Francom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We report on several experiments on combining a rule-based tagger and a trigram tagger for Spanish. The results show that one can boost the accuracy of the best performing n-gram taggers by quickly developing a rough rule-based grammar to complement the statistically induced one and then combining the output of the two. The specific method of combination is crucial for achieving good results. The method provides particularly large gains in accuracy when only a small amount of tagged data is available for training a HMM, as may be the case for lesser-resourced and minority languages.</abstract>
<identifier type="citekey">hulden-francom-2012-boosting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1075_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2114</start>
<end>2117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Boosting statistical tagger accuracy with simple rule-based grammars
%A Hulden, Mans
%A Francom, Jerid
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F hulden-francom-2012-boosting
%X We report on several experiments on combining a rule-based tagger and a trigram tagger for Spanish. The results show that one can boost the accuracy of the best performing n-gram taggers by quickly developing a rough rule-based grammar to complement the statistically induced one and then combining the output of the two. The specific method of combination is crucial for achieving good results. The method provides particularly large gains in accuracy when only a small amount of tagged data is available for training a HMM, as may be the case for lesser-resourced and minority languages.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1075_Paper.pdf
%P 2114-2117
Markdown (Informal)
[Boosting statistical tagger accuracy with simple rule-based grammars](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1075_Paper.pdf) (Hulden & Francom, LREC 2012)
ACL