@inproceedings{tufis-etal-2020-collection,
title = "Collection and Annotation of the {R}omanian Legal Corpus",
author = "Tufi{\textcommabelow{s}}, Dan and
Mitrofan, Maria and
P{\u{a}}i{\textcommabelow{s}}, Vasile and
Ion, Radu and
Coman, Andrei",
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-1.337",
pages = "2773--2777",
abstract = "We present the Romanian legislative corpus which is a valuable linguistic asset for the development of machine translation systems, especially for under-resourced languages. The knowledge that can be extracted from this resource is necessary for a deeper understanding of how law terminology is used and how it can be made more consistent. At this moment the corpus contains more than 140k documents representing the legislative body of Romania. This corpus is processed and annotated at different levels: linguistically (tokenized, lemmatized and pos-tagged), dependency parsed, chunked, named entities identified and labeled with IATE terms and EUROVOC descriptors. Each annotated document has a CONLL-U Plus format consisting in 14 columns, in addition to the standard 10-column format, four other types of annotations were added. Moreover the repository will be periodically updated as new legislative texts are published. These will be automatically collected and transmitted to the processing and annotation pipeline. The access to the corpus will be done through ELRC infrastructure.",
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="tufis-etal-2020-collection">
<titleInfo>
<title>Collection and Annotation of the Romanian Legal Corpus</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">Maria</namePart>
<namePart type="family">Mitrofan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasile</namePart>
<namePart type="family">Păi\textcommabelows</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Ion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Coman</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>We present the Romanian legislative corpus which is a valuable linguistic asset for the development of machine translation systems, especially for under-resourced languages. The knowledge that can be extracted from this resource is necessary for a deeper understanding of how law terminology is used and how it can be made more consistent. At this moment the corpus contains more than 140k documents representing the legislative body of Romania. This corpus is processed and annotated at different levels: linguistically (tokenized, lemmatized and pos-tagged), dependency parsed, chunked, named entities identified and labeled with IATE terms and EUROVOC descriptors. Each annotated document has a CONLL-U Plus format consisting in 14 columns, in addition to the standard 10-column format, four other types of annotations were added. Moreover the repository will be periodically updated as new legislative texts are published. These will be automatically collected and transmitted to the processing and annotation pipeline. The access to the corpus will be done through ELRC infrastructure.</abstract>
<identifier type="citekey">tufis-etal-2020-collection</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.337</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2773</start>
<end>2777</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collection and Annotation of the Romanian Legal Corpus
%A Tufi\textcommabelows, Dan
%A Mitrofan, Maria
%A Păi\textcommabelows, Vasile
%A Ion, Radu
%A Coman, Andrei
%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 tufis-etal-2020-collection
%X We present the Romanian legislative corpus which is a valuable linguistic asset for the development of machine translation systems, especially for under-resourced languages. The knowledge that can be extracted from this resource is necessary for a deeper understanding of how law terminology is used and how it can be made more consistent. At this moment the corpus contains more than 140k documents representing the legislative body of Romania. This corpus is processed and annotated at different levels: linguistically (tokenized, lemmatized and pos-tagged), dependency parsed, chunked, named entities identified and labeled with IATE terms and EUROVOC descriptors. Each annotated document has a CONLL-U Plus format consisting in 14 columns, in addition to the standard 10-column format, four other types of annotations were added. Moreover the repository will be periodically updated as new legislative texts are published. These will be automatically collected and transmitted to the processing and annotation pipeline. The access to the corpus will be done through ELRC infrastructure.
%U https://aclanthology.org/2020.lrec-1.337
%P 2773-2777
Markdown (Informal)
[Collection and Annotation of the Romanian Legal Corpus](https://aclanthology.org/2020.lrec-1.337) (Tufiș et al., LREC 2020)
ACL
- Dan Tufiș, Maria Mitrofan, Vasile Păiș, Radu Ion, and Andrei Coman. 2020. Collection and Annotation of the Romanian Legal Corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2773–2777, Marseille, France. European Language Resources Association.