@inproceedings{petersen-2006-querying,
title = "Querying Both Parallel And Treebank Corpora: Evaluation Of A Corpus Query System",
author = "Petersen, Ulrik",
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/442_pdf.pdf",
abstract = "The last decade has seen a large increase in the number of available corpus query systems. Some of these are optimized for a particular kind of linguistic annotation (e.g., time-aligned, treebank, word-oriented, etc.). In this paper, we report on our own corpus query system, called Emdros. Emdros is very generic, and can be applied to almost any kind of linguistic annotation using almost any linguistic theory. We describe Emdros and its query language, showing some of the benfits that linguists can derive from using Emdros for their corpora. We then describe the underlying database model of Emdros, and show how two corpora can be imported into the system. One of the two is a parallel corpus of Hungarian and English (the Hunglish corpus), while the other is a treebank of German (the TIGER Corpus). In order to evaluate the performance of Emdros, we then run some performance tests. It is shown that Emdros has extremely good performance on small corpora (less than 1 million words), and that it scales well to corpora of many millions of words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petersen-2006-querying">
<titleInfo>
<title>Querying Both Parallel And Treebank Corpora: Evaluation Of A Corpus Query System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulrik</namePart>
<namePart type="family">Petersen</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>The last decade has seen a large increase in the number of available corpus query systems. Some of these are optimized for a particular kind of linguistic annotation (e.g., time-aligned, treebank, word-oriented, etc.). In this paper, we report on our own corpus query system, called Emdros. Emdros is very generic, and can be applied to almost any kind of linguistic annotation using almost any linguistic theory. We describe Emdros and its query language, showing some of the benfits that linguists can derive from using Emdros for their corpora. We then describe the underlying database model of Emdros, and show how two corpora can be imported into the system. One of the two is a parallel corpus of Hungarian and English (the Hunglish corpus), while the other is a treebank of German (the TIGER Corpus). In order to evaluate the performance of Emdros, we then run some performance tests. It is shown that Emdros has extremely good performance on small corpora (less than 1 million words), and that it scales well to corpora of many millions of words.</abstract>
<identifier type="citekey">petersen-2006-querying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/442_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Querying Both Parallel And Treebank Corpora: Evaluation Of A Corpus Query System
%A Petersen, Ulrik
%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 petersen-2006-querying
%X The last decade has seen a large increase in the number of available corpus query systems. Some of these are optimized for a particular kind of linguistic annotation (e.g., time-aligned, treebank, word-oriented, etc.). In this paper, we report on our own corpus query system, called Emdros. Emdros is very generic, and can be applied to almost any kind of linguistic annotation using almost any linguistic theory. We describe Emdros and its query language, showing some of the benfits that linguists can derive from using Emdros for their corpora. We then describe the underlying database model of Emdros, and show how two corpora can be imported into the system. One of the two is a parallel corpus of Hungarian and English (the Hunglish corpus), while the other is a treebank of German (the TIGER Corpus). In order to evaluate the performance of Emdros, we then run some performance tests. It is shown that Emdros has extremely good performance on small corpora (less than 1 million words), and that it scales well to corpora of many millions of words.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/442_pdf.pdf
Markdown (Informal)
[Querying Both Parallel And Treebank Corpora: Evaluation Of A Corpus Query System](http://www.lrec-conf.org/proceedings/lrec2006/pdf/442_pdf.pdf) (Petersen, LREC 2006)
ACL