@inproceedings{grilo-etal-2020-bdcamoes,
title = "The {BDC}am{\~o}es Collection of {P}ortuguese Literary Documents: a Research Resource for Digital Humanities and Language Technology",
author = "Grilo, Sara and
Bolrinha, M{\'a}rcia and
Silva, Jo{\~a}o and
Vaz, Rui and
Branco, Ant{\'o}nio",
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-1.106",
pages = "849--854",
abstract = "This paper presents the BDCam{\~o}es Collection of Portuguese Literary Documents, a new corpus of literary texts written in Portuguese that in its inaugural version includes close to 4 million words from over 200 complete documents from 83 authors in 14 genres, covering a time span from the 16th to the 21st century, and adhering to different orthographic conventions. Many of the texts in the corpus have also been automatically parsed with state-of-the-art language processing tools, forming the BDCam{\~o}es Treebank subcorpus. This set of characteristics makes of BDCam{\~o}es an invaluable resource for research in language technology (e.g. authorship detection, genre classification, etc.) and in language science and digital humanities (e.g. comparative literature, diachronic linguistics, etc.).",
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="grilo-etal-2020-bdcamoes">
<titleInfo>
<title>The BDCamões Collection of Portuguese Literary Documents: a Research Resource for Digital Humanities and Language Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Grilo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Márcia</namePart>
<namePart type="family">Bolrinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Vaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</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 presents the BDCamões Collection of Portuguese Literary Documents, a new corpus of literary texts written in Portuguese that in its inaugural version includes close to 4 million words from over 200 complete documents from 83 authors in 14 genres, covering a time span from the 16th to the 21st century, and adhering to different orthographic conventions. Many of the texts in the corpus have also been automatically parsed with state-of-the-art language processing tools, forming the BDCamões Treebank subcorpus. This set of characteristics makes of BDCamões an invaluable resource for research in language technology (e.g. authorship detection, genre classification, etc.) and in language science and digital humanities (e.g. comparative literature, diachronic linguistics, etc.).</abstract>
<identifier type="citekey">grilo-etal-2020-bdcamoes</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.106</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>849</start>
<end>854</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The BDCamões Collection of Portuguese Literary Documents: a Research Resource for Digital Humanities and Language Technology
%A Grilo, Sara
%A Bolrinha, Márcia
%A Silva, João
%A Vaz, Rui
%A Branco, António
%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 grilo-etal-2020-bdcamoes
%X This paper presents the BDCamões Collection of Portuguese Literary Documents, a new corpus of literary texts written in Portuguese that in its inaugural version includes close to 4 million words from over 200 complete documents from 83 authors in 14 genres, covering a time span from the 16th to the 21st century, and adhering to different orthographic conventions. Many of the texts in the corpus have also been automatically parsed with state-of-the-art language processing tools, forming the BDCamões Treebank subcorpus. This set of characteristics makes of BDCamões an invaluable resource for research in language technology (e.g. authorship detection, genre classification, etc.) and in language science and digital humanities (e.g. comparative literature, diachronic linguistics, etc.).
%U https://aclanthology.org/2020.lrec-1.106
%P 849-854
Markdown (Informal)
[The BDCamões Collection of Portuguese Literary Documents: a Research Resource for Digital Humanities and Language Technology](https://aclanthology.org/2020.lrec-1.106) (Grilo et al., LREC 2020)
ACL