@inproceedings{wellner-vilain-2006-leveraging,
title = "Leveraging Machine Readable Dictionaries in Discriminative Sequence Models",
author = "Wellner, Ben and
Vilain, Marc",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/404_pdf.pdf",
abstract = "Many natural language processing tasks make use of a lexicon typically the words collected from some annotated training data along with their associated properties. We demonstrate here the utility of corpora-independent lexicons derived from machine readable dictionaries. Lexical information is encoded in the form of features in a Conditional Random Field tagger providing improved performance in cases where: i) limited training data is made available ii) the data is case-less and iii) the test data genre or domain is different than that of the training data. We show substantial error reductions, especially on unknown words, for the tasks of part-of-speech tagging and shallow parsing, achieving up to 20{\%} error reduction on Penn TreeBank part-of-speech tagging and up to a 15.7{\%} error reduction for shallow parsing using the CoNLL 2000 data. Our results here point towards a simple, but effective methodology for increasing the adaptability of text processing systems by training models with annotated data in one genre augmented with general lexical information or lexical information pertinent to the target genre (or domain).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wellner-vilain-2006-leveraging">
<titleInfo>
<title>Leveraging Machine Readable Dictionaries in Discriminative Sequence Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Wellner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Vilain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many natural language processing tasks make use of a lexicon typically the words collected from some annotated training data along with their associated properties. We demonstrate here the utility of corpora-independent lexicons derived from machine readable dictionaries. Lexical information is encoded in the form of features in a Conditional Random Field tagger providing improved performance in cases where: i) limited training data is made available ii) the data is case-less and iii) the test data genre or domain is different than that of the training data. We show substantial error reductions, especially on unknown words, for the tasks of part-of-speech tagging and shallow parsing, achieving up to 20% error reduction on Penn TreeBank part-of-speech tagging and up to a 15.7% error reduction for shallow parsing using the CoNLL 2000 data. Our results here point towards a simple, but effective methodology for increasing the adaptability of text processing systems by training models with annotated data in one genre augmented with general lexical information or lexical information pertinent to the target genre (or domain).</abstract>
<identifier type="citekey">wellner-vilain-2006-leveraging</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/404_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Machine Readable Dictionaries in Discriminative Sequence Models
%A Wellner, Ben
%A Vilain, Marc
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F wellner-vilain-2006-leveraging
%X Many natural language processing tasks make use of a lexicon typically the words collected from some annotated training data along with their associated properties. We demonstrate here the utility of corpora-independent lexicons derived from machine readable dictionaries. Lexical information is encoded in the form of features in a Conditional Random Field tagger providing improved performance in cases where: i) limited training data is made available ii) the data is case-less and iii) the test data genre or domain is different than that of the training data. We show substantial error reductions, especially on unknown words, for the tasks of part-of-speech tagging and shallow parsing, achieving up to 20% error reduction on Penn TreeBank part-of-speech tagging and up to a 15.7% error reduction for shallow parsing using the CoNLL 2000 data. Our results here point towards a simple, but effective methodology for increasing the adaptability of text processing systems by training models with annotated data in one genre augmented with general lexical information or lexical information pertinent to the target genre (or domain).
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/404_pdf.pdf
Markdown (Informal)
[Leveraging Machine Readable Dictionaries in Discriminative Sequence Models](http://www.lrec-conf.org/proceedings/lrec2006/pdf/404_pdf.pdf) (Wellner & Vilain, LREC 2006)
ACL