@inproceedings{saulite-etal-2022-latvian,
title = "{L}atvian National Corpora Collection {--} Korpuss.lv",
author = "Saulite, Baiba and
Dar{\c{g}}is, Roberts and
Gruzitis, Normunds and
Auzina, Ilze and
Lev{\=a}ne-Petrova, Krist{\=\i}ne and
Pretkalni{\c{n}}a, Lauma and
Rituma, Laura and
Paikens, Peteris and
Znotins, Arturs and
Strankale, Laine and
Pokratniece, Krist{\=\i}ne and
Poik{\=a}ns, Ilm{\=a}rs and
Barzdins, Guntis and
Skadi{\c{n}}a, Inguna and
Bakl{\=a}ne, Anda and
Saulespur{\=e}ns, Valdis and
Ziedi{\c{n}}{\v{s}}, J{\=a}nis",
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-1.548",
pages = "5123--5129",
abstract = "LNCC is a diverse collection of Latvian language corpora representing both written and spoken language and is useful for both linguistic research and language modelling. The collection is intended to cover diverse Latvian language use cases and all the important text types and genres (e.g. news, social media, blogs, books, scientific texts, debates, essays, etc.), taking into account both quality and size aspects. To reach this objective, LNCC is a continuous multi-institutional and multi-project effort, supported by the Digital Humanities and Language Technology communities in Latvia. LNCC includes a broad range of Latvian texts from the Latvian National Library, Culture Information Systems Centre, Latvian National News Agency, Latvian Parliament, Latvian web crawl, various Latvian publishers, and from the Latvian language corpora created by Institute of Mathematics and Computer Science and its partners, including spoken language corpora. All corpora of LNCC are re-annotated with a uniform morpho-syntactic annotation scheme which enables federated search and consistent linguistics analysis in all the LNCC corpora, as well as facilitates to select and mix various corpora for pre-training large Latvian language models like BERT and GPT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saulite-etal-2022-latvian">
<titleInfo>
<title>Latvian National Corpora Collection – Korpuss.lv</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baiba</namePart>
<namePart type="family">Saulite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberts</namePart>
<namePart type="family">Darģis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Normunds</namePart>
<namePart type="family">Gruzitis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilze</namePart>
<namePart type="family">Auzina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristīne</namePart>
<namePart type="family">Levāne-Petrova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauma</namePart>
<namePart type="family">Pretkalniņa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rituma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peteris</namePart>
<namePart type="family">Paikens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturs</namePart>
<namePart type="family">Znotins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laine</namePart>
<namePart type="family">Strankale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristīne</namePart>
<namePart type="family">Pokratniece</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilmārs</namePart>
<namePart type="family">Poikāns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guntis</namePart>
<namePart type="family">Barzdins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inguna</namePart>
<namePart type="family">Skadiņa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anda</namePart>
<namePart type="family">Baklāne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valdis</namePart>
<namePart type="family">Saulespurēns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jānis</namePart>
<namePart type="family">Ziediņš</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>LNCC is a diverse collection of Latvian language corpora representing both written and spoken language and is useful for both linguistic research and language modelling. The collection is intended to cover diverse Latvian language use cases and all the important text types and genres (e.g. news, social media, blogs, books, scientific texts, debates, essays, etc.), taking into account both quality and size aspects. To reach this objective, LNCC is a continuous multi-institutional and multi-project effort, supported by the Digital Humanities and Language Technology communities in Latvia. LNCC includes a broad range of Latvian texts from the Latvian National Library, Culture Information Systems Centre, Latvian National News Agency, Latvian Parliament, Latvian web crawl, various Latvian publishers, and from the Latvian language corpora created by Institute of Mathematics and Computer Science and its partners, including spoken language corpora. All corpora of LNCC are re-annotated with a uniform morpho-syntactic annotation scheme which enables federated search and consistent linguistics analysis in all the LNCC corpora, as well as facilitates to select and mix various corpora for pre-training large Latvian language models like BERT and GPT.</abstract>
<identifier type="citekey">saulite-etal-2022-latvian</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.548</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5123</start>
<end>5129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latvian National Corpora Collection – Korpuss.lv
%A Saulite, Baiba
%A Darģis, Roberts
%A Gruzitis, Normunds
%A Auzina, Ilze
%A Levāne-Petrova, Kristīne
%A Pretkalniņa, Lauma
%A Rituma, Laura
%A Paikens, Peteris
%A Znotins, Arturs
%A Strankale, Laine
%A Pokratniece, Kristīne
%A Poikāns, Ilmārs
%A Barzdins, Guntis
%A Skadiņa, Inguna
%A Baklāne, Anda
%A Saulespurēns, Valdis
%A Ziediņš, Jānis
%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 saulite-etal-2022-latvian
%X LNCC is a diverse collection of Latvian language corpora representing both written and spoken language and is useful for both linguistic research and language modelling. The collection is intended to cover diverse Latvian language use cases and all the important text types and genres (e.g. news, social media, blogs, books, scientific texts, debates, essays, etc.), taking into account both quality and size aspects. To reach this objective, LNCC is a continuous multi-institutional and multi-project effort, supported by the Digital Humanities and Language Technology communities in Latvia. LNCC includes a broad range of Latvian texts from the Latvian National Library, Culture Information Systems Centre, Latvian National News Agency, Latvian Parliament, Latvian web crawl, various Latvian publishers, and from the Latvian language corpora created by Institute of Mathematics and Computer Science and its partners, including spoken language corpora. All corpora of LNCC are re-annotated with a uniform morpho-syntactic annotation scheme which enables federated search and consistent linguistics analysis in all the LNCC corpora, as well as facilitates to select and mix various corpora for pre-training large Latvian language models like BERT and GPT.
%U https://aclanthology.org/2022.lrec-1.548
%P 5123-5129
Markdown (Informal)
[Latvian National Corpora Collection – Korpuss.lv](https://aclanthology.org/2022.lrec-1.548) (Saulite et al., LREC 2022)
ACL
- Baiba Saulite, Roberts Darģis, Normunds Gruzitis, Ilze Auzina, Kristīne Levāne-Petrova, Lauma Pretkalniņa, Laura Rituma, Peteris Paikens, Arturs Znotins, Laine Strankale, Kristīne Pokratniece, Ilmārs Poikāns, Guntis Barzdins, Inguna Skadiņa, Anda Baklāne, Valdis Saulespurēns, and Jānis Ziediņš. 2022. Latvian National Corpora Collection – Korpuss.lv. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5123–5129, Marseille, France. European Language Resources Association.