@inproceedings{zhang-kordoni-2006-automated,
title = "Automated Deep Lexical Acquisition for Robust Open Texts Processing",
author = "Zhang, Yi and
Kordoni, Valia",
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/464_pdf.pdf",
abstract = "In this paper, we report on methods to detect and repair lexical errors for deep grammars. The lack of coverage has for long been the major problem for deep processing. The existence of various errors in the hand-crafted large grammars prevents their usage in real applications. The manual detection and repair of errors requires asignificant amount of human effort. An experiment with the British National Corpus shows about 70{\%} of the sentences contain unknownword(s) for the English Resource Grammar. With the help of error mining methods, many lexical errors are discovered, which cause a large part of the parsing failures. Moreover, with a lexical type predictor based on a maximum entropy model, new lexical entries are automatically generated. The contribution of various features for the model is evaluated. With the disambiguated full parsing results, the precision of the predictor is enhanced significantly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-kordoni-2006-automated">
<titleInfo>
<title>Automated Deep Lexical Acquisition for Robust Open Texts Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valia</namePart>
<namePart type="family">Kordoni</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>In this paper, we report on methods to detect and repair lexical errors for deep grammars. The lack of coverage has for long been the major problem for deep processing. The existence of various errors in the hand-crafted large grammars prevents their usage in real applications. The manual detection and repair of errors requires asignificant amount of human effort. An experiment with the British National Corpus shows about 70% of the sentences contain unknownword(s) for the English Resource Grammar. With the help of error mining methods, many lexical errors are discovered, which cause a large part of the parsing failures. Moreover, with a lexical type predictor based on a maximum entropy model, new lexical entries are automatically generated. The contribution of various features for the model is evaluated. With the disambiguated full parsing results, the precision of the predictor is enhanced significantly.</abstract>
<identifier type="citekey">zhang-kordoni-2006-automated</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/464_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Deep Lexical Acquisition for Robust Open Texts Processing
%A Zhang, Yi
%A Kordoni, Valia
%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 zhang-kordoni-2006-automated
%X In this paper, we report on methods to detect and repair lexical errors for deep grammars. The lack of coverage has for long been the major problem for deep processing. The existence of various errors in the hand-crafted large grammars prevents their usage in real applications. The manual detection and repair of errors requires asignificant amount of human effort. An experiment with the British National Corpus shows about 70% of the sentences contain unknownword(s) for the English Resource Grammar. With the help of error mining methods, many lexical errors are discovered, which cause a large part of the parsing failures. Moreover, with a lexical type predictor based on a maximum entropy model, new lexical entries are automatically generated. The contribution of various features for the model is evaluated. With the disambiguated full parsing results, the precision of the predictor is enhanced significantly.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/464_pdf.pdf
Markdown (Informal)
[Automated Deep Lexical Acquisition for Robust Open Texts Processing](http://www.lrec-conf.org/proceedings/lrec2006/pdf/464_pdf.pdf) (Zhang & Kordoni, LREC 2006)
ACL