@inproceedings{stepanek-pajas-2010-querying,
title = "Querying Diverse Treebanks in a Uniform Way",
author = "{\v{S}}t{\v{e}}p{\'a}nek, Jan and
Pajas, Petr",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/381_Paper.pdf",
abstract = "This paper presents a system for querying treebanks in a uniform way. The system is able to work with both dependency and constituency based treebanks in any language. We demonstrate its abilities on 11 different treebanks. The query language used by the system provides many features not available in other existing systems while still keeping the performance efficient. The paper also describes the conversion of ten treebanks into a common XML-based format used by the system, touching the question of standards and formats. The paper then shows several examples of linguistically interesting questions that the system is able to answer, for example browsing verbal clauses without subjects or extraposed relative clauses, generating the underlying grammar in a constituency treebank, searching for non-projective edges in a dependency treebank, or word-order typology of a language based on the treebank. The performance of several implementations of the system is also discussed by measuring the time requirements of some of the queries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stepanek-pajas-2010-querying">
<titleInfo>
<title>Querying Diverse Treebanks in a Uniform Way</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Štěpánek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Pajas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a system for querying treebanks in a uniform way. The system is able to work with both dependency and constituency based treebanks in any language. We demonstrate its abilities on 11 different treebanks. The query language used by the system provides many features not available in other existing systems while still keeping the performance efficient. The paper also describes the conversion of ten treebanks into a common XML-based format used by the system, touching the question of standards and formats. The paper then shows several examples of linguistically interesting questions that the system is able to answer, for example browsing verbal clauses without subjects or extraposed relative clauses, generating the underlying grammar in a constituency treebank, searching for non-projective edges in a dependency treebank, or word-order typology of a language based on the treebank. The performance of several implementations of the system is also discussed by measuring the time requirements of some of the queries.</abstract>
<identifier type="citekey">stepanek-pajas-2010-querying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/381_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Querying Diverse Treebanks in a Uniform Way
%A Štěpánek, Jan
%A Pajas, Petr
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F stepanek-pajas-2010-querying
%X This paper presents a system for querying treebanks in a uniform way. The system is able to work with both dependency and constituency based treebanks in any language. We demonstrate its abilities on 11 different treebanks. The query language used by the system provides many features not available in other existing systems while still keeping the performance efficient. The paper also describes the conversion of ten treebanks into a common XML-based format used by the system, touching the question of standards and formats. The paper then shows several examples of linguistically interesting questions that the system is able to answer, for example browsing verbal clauses without subjects or extraposed relative clauses, generating the underlying grammar in a constituency treebank, searching for non-projective edges in a dependency treebank, or word-order typology of a language based on the treebank. The performance of several implementations of the system is also discussed by measuring the time requirements of some of the queries.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/381_Paper.pdf
Markdown (Informal)
[Querying Diverse Treebanks in a Uniform Way](http://www.lrec-conf.org/proceedings/lrec2010/pdf/381_Paper.pdf) (Štěpánek & Pajas, LREC 2010)
ACL
- Jan Štěpánek and Petr Pajas. 2010. Querying Diverse Treebanks in a Uniform Way. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).