@inproceedings{deoskar-rooth-2008-induction,
title = "Induction of Treebank-Aligned Lexical Resources",
author = "Deoskar, Tejaswini and
Rooth, Mats",
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/798_paper.pdf",
abstract = "We describe the induction of lexical resources from unannotated corpora that are aligned with treebank grammars, providing a systematic correspondence between features in the lexical resource and a treebank syntactic resource. We first describe a methodology based on parsing technology for augmenting a treebank database with linguistic features. A PCFG containing these features is created from the augmented treebank. We then use a procedure based on the inside-outside algorithm to learn lexical resources aligned with the treebank PCFG from large unannotated corpora. The method has been applied in creating a feature-annotated English treebank based on the Penn Treebank. The unsupervised estimation procedure gives a substantial error reduction (up to 31.6{\%}) on the task of learning the subcategorization preference of novel verbs that are not present in the annotated training sample.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deoskar-rooth-2008-induction">
<titleInfo>
<title>Induction of Treebank-Aligned Lexical Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tejaswini</namePart>
<namePart type="family">Deoskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mats</namePart>
<namePart type="family">Rooth</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>We describe the induction of lexical resources from unannotated corpora that are aligned with treebank grammars, providing a systematic correspondence between features in the lexical resource and a treebank syntactic resource. We first describe a methodology based on parsing technology for augmenting a treebank database with linguistic features. A PCFG containing these features is created from the augmented treebank. We then use a procedure based on the inside-outside algorithm to learn lexical resources aligned with the treebank PCFG from large unannotated corpora. The method has been applied in creating a feature-annotated English treebank based on the Penn Treebank. The unsupervised estimation procedure gives a substantial error reduction (up to 31.6%) on the task of learning the subcategorization preference of novel verbs that are not present in the annotated training sample.</abstract>
<identifier type="citekey">deoskar-rooth-2008-induction</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/798_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Induction of Treebank-Aligned Lexical Resources
%A Deoskar, Tejaswini
%A Rooth, Mats
%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 deoskar-rooth-2008-induction
%X We describe the induction of lexical resources from unannotated corpora that are aligned with treebank grammars, providing a systematic correspondence between features in the lexical resource and a treebank syntactic resource. We first describe a methodology based on parsing technology for augmenting a treebank database with linguistic features. A PCFG containing these features is created from the augmented treebank. We then use a procedure based on the inside-outside algorithm to learn lexical resources aligned with the treebank PCFG from large unannotated corpora. The method has been applied in creating a feature-annotated English treebank based on the Penn Treebank. The unsupervised estimation procedure gives a substantial error reduction (up to 31.6%) on the task of learning the subcategorization preference of novel verbs that are not present in the annotated training sample.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/798_paper.pdf
Markdown (Informal)
[Induction of Treebank-Aligned Lexical Resources](http://www.lrec-conf.org/proceedings/lrec2008/pdf/798_paper.pdf) (Deoskar & Rooth, LREC 2008)
ACL
- Tejaswini Deoskar and Mats Rooth. 2008. Induction of Treebank-Aligned Lexical Resources. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).