@inproceedings{coole-etal-2020-lexidb,
title = "{L}exi{DB}: Patterns {\&} Methods for Corpus Linguistic Database Management",
author = "Coole, Matthew and
Rayson, Paul and
Mariani, John",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.383",
pages = "3128--3135",
abstract = "LexiDB is a tool for storing, managing and querying corpus data. In contrast to other database management systems (DBMSs), it is designed specifically for text corpora. It improves on other corpus management systems (CMSs) because data can be added and deleted from corpora on the fly with the ability to add live data to existing corpora. LexiDB sits between these two categories of DBMSs and CMSs, more specialised to language data than a general purpose DBMS but more flexible than a traditional static corpus management system. Previous work has demonstrated the scalability of LexiDB in response to the growing need to be able to scale out for ever growing corpus datasets. Here, we present the patterns and methods developed in LexiDB for storage, retrieval and querying of multi-level annotated corpus data. These techniques are evaluated and compared to an existing CMS (Corpus Workbench CWB - CQP) and indexer (Lucene). We find that LexiDB consistently outperforms existing tools for corpus queries. This is particularly apparent with large corpora and when handling queries with large result sets",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coole-etal-2020-lexidb">
<titleInfo>
<title>LexiDB: Patterns & Methods for Corpus Linguistic Database Management</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Coole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>LexiDB is a tool for storing, managing and querying corpus data. In contrast to other database management systems (DBMSs), it is designed specifically for text corpora. It improves on other corpus management systems (CMSs) because data can be added and deleted from corpora on the fly with the ability to add live data to existing corpora. LexiDB sits between these two categories of DBMSs and CMSs, more specialised to language data than a general purpose DBMS but more flexible than a traditional static corpus management system. Previous work has demonstrated the scalability of LexiDB in response to the growing need to be able to scale out for ever growing corpus datasets. Here, we present the patterns and methods developed in LexiDB for storage, retrieval and querying of multi-level annotated corpus data. These techniques are evaluated and compared to an existing CMS (Corpus Workbench CWB - CQP) and indexer (Lucene). We find that LexiDB consistently outperforms existing tools for corpus queries. This is particularly apparent with large corpora and when handling queries with large result sets</abstract>
<identifier type="citekey">coole-etal-2020-lexidb</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.383</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3128</start>
<end>3135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LexiDB: Patterns & Methods for Corpus Linguistic Database Management
%A Coole, Matthew
%A Rayson, Paul
%A Mariani, John
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F coole-etal-2020-lexidb
%X LexiDB is a tool for storing, managing and querying corpus data. In contrast to other database management systems (DBMSs), it is designed specifically for text corpora. It improves on other corpus management systems (CMSs) because data can be added and deleted from corpora on the fly with the ability to add live data to existing corpora. LexiDB sits between these two categories of DBMSs and CMSs, more specialised to language data than a general purpose DBMS but more flexible than a traditional static corpus management system. Previous work has demonstrated the scalability of LexiDB in response to the growing need to be able to scale out for ever growing corpus datasets. Here, we present the patterns and methods developed in LexiDB for storage, retrieval and querying of multi-level annotated corpus data. These techniques are evaluated and compared to an existing CMS (Corpus Workbench CWB - CQP) and indexer (Lucene). We find that LexiDB consistently outperforms existing tools for corpus queries. This is particularly apparent with large corpora and when handling queries with large result sets
%U https://aclanthology.org/2020.lrec-1.383
%P 3128-3135
Markdown (Informal)
[LexiDB: Patterns & Methods for Corpus Linguistic Database Management](https://aclanthology.org/2020.lrec-1.383) (Coole et al., LREC 2020)
ACL