@inproceedings{bick-2006-turning,
title = "Turning a Dependency Treebank into a {PSG}-style Constituent Treebank",
author = "Bick, Eckhard",
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/452_pdf.pdf",
abstract = "In this paper, we present and evaluate a new method to convert Constraint Grammar (CG) parses of running text into Constituent Treebanks. The conversion is two-step - first a grammar-based method is used to bridge the gap between raw CG annotation and full dependency structure, then phrase structure bracketing and non-terminal nodes are introduced by clustering sister dependents, effectively building one syntactic treebank on top of another. The method is compared with another approach (Bick 2003-2), where constituent structures are arrived at by employing a function-tag based Phrase Structure Grammar (PSG). Results are evaluated on a small reference corpus for both raw and revised CG input, with bracketing F-Scores of 87.5{\%} for raw text and 97.1{\%} for revised CG input, and a raw text edge label accuracy of 95.9{\%} for forms and 86{\%} for functions, or 99.7{\%} and 99.4{\%}, respectively, for revised CG. By applying the tools to the CG-only part of the Danish Arboretum treebank we were able to increase the size of the treebank by 86{\%}, from 197.400 to 367.500 words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bick-2006-turning">
<titleInfo>
<title>Turning a Dependency Treebank into a PSG-style Constituent Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eckhard</namePart>
<namePart type="family">Bick</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 present and evaluate a new method to convert Constraint Grammar (CG) parses of running text into Constituent Treebanks. The conversion is two-step - first a grammar-based method is used to bridge the gap between raw CG annotation and full dependency structure, then phrase structure bracketing and non-terminal nodes are introduced by clustering sister dependents, effectively building one syntactic treebank on top of another. The method is compared with another approach (Bick 2003-2), where constituent structures are arrived at by employing a function-tag based Phrase Structure Grammar (PSG). Results are evaluated on a small reference corpus for both raw and revised CG input, with bracketing F-Scores of 87.5% for raw text and 97.1% for revised CG input, and a raw text edge label accuracy of 95.9% for forms and 86% for functions, or 99.7% and 99.4%, respectively, for revised CG. By applying the tools to the CG-only part of the Danish Arboretum treebank we were able to increase the size of the treebank by 86%, from 197.400 to 367.500 words.</abstract>
<identifier type="citekey">bick-2006-turning</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/452_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Turning a Dependency Treebank into a PSG-style Constituent Treebank
%A Bick, Eckhard
%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 bick-2006-turning
%X In this paper, we present and evaluate a new method to convert Constraint Grammar (CG) parses of running text into Constituent Treebanks. The conversion is two-step - first a grammar-based method is used to bridge the gap between raw CG annotation and full dependency structure, then phrase structure bracketing and non-terminal nodes are introduced by clustering sister dependents, effectively building one syntactic treebank on top of another. The method is compared with another approach (Bick 2003-2), where constituent structures are arrived at by employing a function-tag based Phrase Structure Grammar (PSG). Results are evaluated on a small reference corpus for both raw and revised CG input, with bracketing F-Scores of 87.5% for raw text and 97.1% for revised CG input, and a raw text edge label accuracy of 95.9% for forms and 86% for functions, or 99.7% and 99.4%, respectively, for revised CG. By applying the tools to the CG-only part of the Danish Arboretum treebank we were able to increase the size of the treebank by 86%, from 197.400 to 367.500 words.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/452_pdf.pdf
Markdown (Informal)
[Turning a Dependency Treebank into a PSG-style Constituent Treebank](http://www.lrec-conf.org/proceedings/lrec2006/pdf/452_pdf.pdf) (Bick, LREC 2006)
ACL