@inproceedings{midrigan-ciochina-etal-2020-resources,
title = "Resources in Underrepresented Languages: Building a Representative {R}omanian Corpus",
author = "Midrigan - Ciochina, Ludmila and
Boyd, Victoria and
Sanchez-Ortega, Lucila and
Malancea{\_}Malac, Diana and
Midrigan, Doina and
Corina, David P.",
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-1.402",
pages = "3291--3296",
abstract = "The effort in the field of Linguistics to develop theories that aim to explain language-dependent effects on language processing is greatly facilitated by the availability of reliable resources representing different languages. This project presents a detailed description of the process of creating a large and representative corpus in Romanian {--} a relatively under-resourced language with unique structural and typological characteristics, that can be used as a reliable language resource for linguistic studies. The decisions that have guided the construction of the corpus, including the type of corpus, its size and component resource files are discussed. Issues related to data collection, data organization and storage, as well as characteristics of the data included in the corpus are described. Currently, the corpus has approximately 5,500,000 tokens originating from written text and 100,000 tokens of spoken language. it includes language samples that represent a wide variety of registers (i.e. written language - 16 registers and 5 registers of spoken language), as well as different authors and speakers",
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="midrigan-ciochina-etal-2020-resources">
<titleInfo>
<title>Resources in Underrepresented Languages: Building a Representative Romanian Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ludmila</namePart>
<namePart type="family">Midrigan - Ciochina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Boyd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucila</namePart>
<namePart type="family">Sanchez-Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Malancea_Malac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doina</namePart>
<namePart type="family">Midrigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Corina</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>The effort in the field of Linguistics to develop theories that aim to explain language-dependent effects on language processing is greatly facilitated by the availability of reliable resources representing different languages. This project presents a detailed description of the process of creating a large and representative corpus in Romanian – a relatively under-resourced language with unique structural and typological characteristics, that can be used as a reliable language resource for linguistic studies. The decisions that have guided the construction of the corpus, including the type of corpus, its size and component resource files are discussed. Issues related to data collection, data organization and storage, as well as characteristics of the data included in the corpus are described. Currently, the corpus has approximately 5,500,000 tokens originating from written text and 100,000 tokens of spoken language. it includes language samples that represent a wide variety of registers (i.e. written language - 16 registers and 5 registers of spoken language), as well as different authors and speakers</abstract>
<identifier type="citekey">midrigan-ciochina-etal-2020-resources</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.402</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3291</start>
<end>3296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Resources in Underrepresented Languages: Building a Representative Romanian Corpus
%A Midrigan - Ciochina, Ludmila
%A Boyd, Victoria
%A Sanchez-Ortega, Lucila
%A Malancea_Malac, Diana
%A Midrigan, Doina
%A Corina, David P.
%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 midrigan-ciochina-etal-2020-resources
%X The effort in the field of Linguistics to develop theories that aim to explain language-dependent effects on language processing is greatly facilitated by the availability of reliable resources representing different languages. This project presents a detailed description of the process of creating a large and representative corpus in Romanian – a relatively under-resourced language with unique structural and typological characteristics, that can be used as a reliable language resource for linguistic studies. The decisions that have guided the construction of the corpus, including the type of corpus, its size and component resource files are discussed. Issues related to data collection, data organization and storage, as well as characteristics of the data included in the corpus are described. Currently, the corpus has approximately 5,500,000 tokens originating from written text and 100,000 tokens of spoken language. it includes language samples that represent a wide variety of registers (i.e. written language - 16 registers and 5 registers of spoken language), as well as different authors and speakers
%U https://aclanthology.org/2020.lrec-1.402
%P 3291-3296
Markdown (Informal)
[Resources in Underrepresented Languages: Building a Representative Romanian Corpus](https://aclanthology.org/2020.lrec-1.402) (Midrigan - Ciochina et al., LREC 2020)
ACL