@inproceedings{varadi-etal-2022-introducing,
title = "Introducing the {CURLICAT} Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources",
author = "V{\'a}radi, Tam{\'a}s and
Ny{\'e}ki, Bence and
Koeva, Svetla and
Tadi{\'c}, Marko and
{\v{S}}tefanec, Vanja and
Ogrodniczuk, Maciej and
Nito{\'n}, Bart{\l}omiej and
P{\k{e}}zik, Piotr and
Barbu Mititelu, Verginica and
Irimia, Elena and
Mitrofan, Maria and
Tufi{\textcommabelow{s}}, Dan and
Garab{\'\i}k, Radovan and
Krek, Simon and
Repar, Andra{\v{z}}",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.11",
pages = "100--108",
abstract = "This article presents the current outcomes of the CURLICAT CEF Telecom project, which aims to collect and deeply annotate a set of large corpora from selected domains. The CURLICAT corpus includes 7 monolingual corpora (Bulgarian, Croatian, Hungarian, Polish, Romanian, Slovak and Slovenian) containing selected samples from respective national corpora. These corpora are automatically tokenized, lemmatized and morphologically analysed and the named entities annotated. The annotations are uniformly provided for each language specific corpus while the common metadata schema is harmonised across the languages. Additionally, the corpora are annotated for IATE terms in all languages. The file format is CoNLL-U Plus format, containing the ten columns specific to the CoNLL-U format and three extra columns specific to our corpora as defined by Var{\'a}di et al. (2020). The CURLICAT corpora represent a rich and valuable source not just for training NMT models, but also for further studies and developments in machine learning, cross-lingual terminological data extraction and classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varadi-etal-2022-introducing">
<titleInfo>
<title>Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Váradi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bence</namePart>
<namePart type="family">Nyéki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Koeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Tadić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanja</namePart>
<namePart type="family">Štefanec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bartłomiej</namePart>
<namePart type="family">Nitoń</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Pęzik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="family">Barbu 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">Maria</namePart>
<namePart type="family">Mitrofan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Radovan</namePart>
<namePart type="family">Garabík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andraž</namePart>
<namePart type="family">Repar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>This article presents the current outcomes of the CURLICAT CEF Telecom project, which aims to collect and deeply annotate a set of large corpora from selected domains. The CURLICAT corpus includes 7 monolingual corpora (Bulgarian, Croatian, Hungarian, Polish, Romanian, Slovak and Slovenian) containing selected samples from respective national corpora. These corpora are automatically tokenized, lemmatized and morphologically analysed and the named entities annotated. The annotations are uniformly provided for each language specific corpus while the common metadata schema is harmonised across the languages. Additionally, the corpora are annotated for IATE terms in all languages. The file format is CoNLL-U Plus format, containing the ten columns specific to the CoNLL-U format and three extra columns specific to our corpora as defined by Varádi et al. (2020). The CURLICAT corpora represent a rich and valuable source not just for training NMT models, but also for further studies and developments in machine learning, cross-lingual terminological data extraction and classification.</abstract>
<identifier type="citekey">varadi-etal-2022-introducing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.11</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>100</start>
<end>108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources
%A Váradi, Tamás
%A Nyéki, Bence
%A Koeva, Svetla
%A Tadić, Marko
%A Štefanec, Vanja
%A Ogrodniczuk, Maciej
%A Nitoń, Bartłomiej
%A Pęzik, Piotr
%A Barbu Mititelu, Verginica
%A Irimia, Elena
%A Mitrofan, Maria
%A Tufi\textcommabelows, Dan
%A Garabík, Radovan
%A Krek, Simon
%A Repar, Andraž
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F varadi-etal-2022-introducing
%X This article presents the current outcomes of the CURLICAT CEF Telecom project, which aims to collect and deeply annotate a set of large corpora from selected domains. The CURLICAT corpus includes 7 monolingual corpora (Bulgarian, Croatian, Hungarian, Polish, Romanian, Slovak and Slovenian) containing selected samples from respective national corpora. These corpora are automatically tokenized, lemmatized and morphologically analysed and the named entities annotated. The annotations are uniformly provided for each language specific corpus while the common metadata schema is harmonised across the languages. Additionally, the corpora are annotated for IATE terms in all languages. The file format is CoNLL-U Plus format, containing the ten columns specific to the CoNLL-U format and three extra columns specific to our corpora as defined by Varádi et al. (2020). The CURLICAT corpora represent a rich and valuable source not just for training NMT models, but also for further studies and developments in machine learning, cross-lingual terminological data extraction and classification.
%U https://aclanthology.org/2022.lrec-1.11
%P 100-108
Markdown (Informal)
[Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources](https://aclanthology.org/2022.lrec-1.11) (Váradi et al., LREC 2022)
ACL
- Tamás Váradi, Bence Nyéki, Svetla Koeva, Marko Tadić, Vanja Štefanec, Maciej Ogrodniczuk, Bartłomiej Nitoń, Piotr Pęzik, Verginica Barbu Mititelu, Elena Irimia, Maria Mitrofan, Dan Tufiș, Radovan Garabík, Simon Krek, and Andraž Repar. 2022. Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 100–108, Marseille, France. European Language Resources Association.