@inproceedings{aulamo-etal-2020-opustools,
title = "{O}pus{T}ools and Parallel Corpus Diagnostics",
author = {Aulamo, Mikko and
Sulubacak, Umut and
Virpioja, Sami and
Tiedemann, J{\"o}rg},
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-1.467",
pages = "3782--3789",
abstract = "This paper introduces OpusTools, a package for downloading and processing parallel corpora included in the OPUS corpus collection. The package implements tools for accessing compressed data in their archived release format and make it possible to easily convert between common formats. OpusTools also includes tools for language identification and data filtering as well as tools for importing data from various sources into the OPUS format. We show the use of these tools in parallel corpus creation and data diagnostics. The latter is especially useful for the identification of potential problems and errors in the extensive data set. Using these tools, we can now monitor the validity of data sets and improve the overall quality and consitency of the data collection.",
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="aulamo-etal-2020-opustools">
<titleInfo>
<title>OpusTools and Parallel Corpus Diagnostics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Aulamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Umut</namePart>
<namePart type="family">Sulubacak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Virpioja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</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>This paper introduces OpusTools, a package for downloading and processing parallel corpora included in the OPUS corpus collection. The package implements tools for accessing compressed data in their archived release format and make it possible to easily convert between common formats. OpusTools also includes tools for language identification and data filtering as well as tools for importing data from various sources into the OPUS format. We show the use of these tools in parallel corpus creation and data diagnostics. The latter is especially useful for the identification of potential problems and errors in the extensive data set. Using these tools, we can now monitor the validity of data sets and improve the overall quality and consitency of the data collection.</abstract>
<identifier type="citekey">aulamo-etal-2020-opustools</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.467</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3782</start>
<end>3789</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpusTools and Parallel Corpus Diagnostics
%A Aulamo, Mikko
%A Sulubacak, Umut
%A Virpioja, Sami
%A Tiedemann, Jörg
%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 aulamo-etal-2020-opustools
%X This paper introduces OpusTools, a package for downloading and processing parallel corpora included in the OPUS corpus collection. The package implements tools for accessing compressed data in their archived release format and make it possible to easily convert between common formats. OpusTools also includes tools for language identification and data filtering as well as tools for importing data from various sources into the OPUS format. We show the use of these tools in parallel corpus creation and data diagnostics. The latter is especially useful for the identification of potential problems and errors in the extensive data set. Using these tools, we can now monitor the validity of data sets and improve the overall quality and consitency of the data collection.
%U https://aclanthology.org/2020.lrec-1.467
%P 3782-3789
Markdown (Informal)
[OpusTools and Parallel Corpus Diagnostics](https://aclanthology.org/2020.lrec-1.467) (Aulamo et al., LREC 2020)
ACL
- Mikko Aulamo, Umut Sulubacak, Sami Virpioja, and Jörg Tiedemann. 2020. OpusTools and Parallel Corpus Diagnostics. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3782–3789, Marseille, France. European Language Resources Association.