@inproceedings{tufis-etal-2016-ipr,
title = "The {IPR}-cleared Corpus of Contemporary Written and Spoken {R}omanian Language",
author = "Tufi{\textcommabelow{s}}, Dan and
Mititelu, Verginica Barbu and
Irimia, Elena and
Dumitrescu, {\textcommabelow{S}}tefan Daniel and
Boro{\textcommabelow{s}}, Tiberiu",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1399",
pages = "2516--2521",
abstract = "The article describes the current status of a large national project, CoRoLa, aiming at building a reference corpus for the contemporary Romanian language. Unlike many other national corpora, CoRoLa contains only - IPR cleared texts and speech data, obtained from some of the country{'}s most representative publishing houses, broadcasting agencies, editorial offices, newspapers and popular bloggers. For the written component 500 million tokens are targeted and for the oral one 300 hours of recordings. The choice of texts is done according to their functional style, domain and subdomain, also with an eye to the international practice. A metadata file (following the CMDI model) is associated to each text file. Collected texts are cleaned and transformed in a format compatible with the tools for automatic processing (segmentation, tokenization, lemmatization, part-of-speech tagging). The paper also presents up-to-date statistics about the structure of the corpus almost two years before its official launching. The corpus will be freely available for searching. Users will be able to download the results of their searches and those original files when not against stipulations in the protocols we have with text providers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufis-etal-2016-ipr">
<titleInfo>
<title>The IPR-cleared Corpus of Contemporary Written and Spoken Romanian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufi\textcommabelows</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Irimia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">\textcommabelowStefan</namePart>
<namePart type="given">Daniel</namePart>
<namePart type="family">Dumitrescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiberiu</namePart>
<namePart type="family">Boro\textcommabelows</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The article describes the current status of a large national project, CoRoLa, aiming at building a reference corpus for the contemporary Romanian language. Unlike many other national corpora, CoRoLa contains only - IPR cleared texts and speech data, obtained from some of the country’s most representative publishing houses, broadcasting agencies, editorial offices, newspapers and popular bloggers. For the written component 500 million tokens are targeted and for the oral one 300 hours of recordings. The choice of texts is done according to their functional style, domain and subdomain, also with an eye to the international practice. A metadata file (following the CMDI model) is associated to each text file. Collected texts are cleaned and transformed in a format compatible with the tools for automatic processing (segmentation, tokenization, lemmatization, part-of-speech tagging). The paper also presents up-to-date statistics about the structure of the corpus almost two years before its official launching. The corpus will be freely available for searching. Users will be able to download the results of their searches and those original files when not against stipulations in the protocols we have with text providers.</abstract>
<identifier type="citekey">tufis-etal-2016-ipr</identifier>
<location>
<url>https://aclanthology.org/L16-1399</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2516</start>
<end>2521</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The IPR-cleared Corpus of Contemporary Written and Spoken Romanian Language
%A Tufi\textcommabelows, Dan
%A Mititelu, Verginica Barbu
%A Irimia, Elena
%A Dumitrescu, \textcommabelowStefan Daniel
%A Boro\textcommabelows, Tiberiu
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F tufis-etal-2016-ipr
%X The article describes the current status of a large national project, CoRoLa, aiming at building a reference corpus for the contemporary Romanian language. Unlike many other national corpora, CoRoLa contains only - IPR cleared texts and speech data, obtained from some of the country’s most representative publishing houses, broadcasting agencies, editorial offices, newspapers and popular bloggers. For the written component 500 million tokens are targeted and for the oral one 300 hours of recordings. The choice of texts is done according to their functional style, domain and subdomain, also with an eye to the international practice. A metadata file (following the CMDI model) is associated to each text file. Collected texts are cleaned and transformed in a format compatible with the tools for automatic processing (segmentation, tokenization, lemmatization, part-of-speech tagging). The paper also presents up-to-date statistics about the structure of the corpus almost two years before its official launching. The corpus will be freely available for searching. Users will be able to download the results of their searches and those original files when not against stipulations in the protocols we have with text providers.
%U https://aclanthology.org/L16-1399
%P 2516-2521
Markdown (Informal)
[The IPR-cleared Corpus of Contemporary Written and Spoken Romanian Language](https://aclanthology.org/L16-1399) (Tufiș et al., LREC 2016)
ACL