@inproceedings{verdonik-etal-2024-gos-2,
title = "Gos 2: A New Reference Corpus of Spoken {S}lovenian",
author = "Verdonik, Darinka and
Dobrovoljc, Kaja and
Erjavec, Toma{\v{z}} and
Ljube{\v{s}}i{\'c}, Nikola",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.691",
pages = "7825--7830",
abstract = "This paper introduces a new version of the Gos reference corpus of spoken Slovenian, which was recently extended to more than double the original size (300 hours, 2.4 million words) by adding speech recordings and transcriptions from two related initiatives, the Gos VideoLectures corpus of public academic speech, and the Artur speech recognition database. We describe this process by first presenting the criteria guiding the balanced selection of the newly added data and the challenges encountered when merging language resources with divergent designs, followed by the presentation of other major enhancements of the new Gos corpus, such as improvements in lemmatization and morphosyntactic annotation, word-level speech alignment, a new XML schema and the development of a specialized online concordancer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verdonik-etal-2024-gos-2">
<titleInfo>
<title>Gos 2: A New Reference Corpus of Spoken Slovenian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darinka</namePart>
<namePart type="family">Verdonik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaja</namePart>
<namePart type="family">Dobrovoljc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a new version of the Gos reference corpus of spoken Slovenian, which was recently extended to more than double the original size (300 hours, 2.4 million words) by adding speech recordings and transcriptions from two related initiatives, the Gos VideoLectures corpus of public academic speech, and the Artur speech recognition database. We describe this process by first presenting the criteria guiding the balanced selection of the newly added data and the challenges encountered when merging language resources with divergent designs, followed by the presentation of other major enhancements of the new Gos corpus, such as improvements in lemmatization and morphosyntactic annotation, word-level speech alignment, a new XML schema and the development of a specialized online concordancer.</abstract>
<identifier type="citekey">verdonik-etal-2024-gos-2</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.691</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7825</start>
<end>7830</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gos 2: A New Reference Corpus of Spoken Slovenian
%A Verdonik, Darinka
%A Dobrovoljc, Kaja
%A Erjavec, Tomaž
%A Ljubešić, Nikola
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F verdonik-etal-2024-gos-2
%X This paper introduces a new version of the Gos reference corpus of spoken Slovenian, which was recently extended to more than double the original size (300 hours, 2.4 million words) by adding speech recordings and transcriptions from two related initiatives, the Gos VideoLectures corpus of public academic speech, and the Artur speech recognition database. We describe this process by first presenting the criteria guiding the balanced selection of the newly added data and the challenges encountered when merging language resources with divergent designs, followed by the presentation of other major enhancements of the new Gos corpus, such as improvements in lemmatization and morphosyntactic annotation, word-level speech alignment, a new XML schema and the development of a specialized online concordancer.
%U https://aclanthology.org/2024.lrec-main.691
%P 7825-7830
Markdown (Informal)
[Gos 2: A New Reference Corpus of Spoken Slovenian](https://aclanthology.org/2024.lrec-main.691) (Verdonik et al., LREC-COLING 2024)
ACL
- Darinka Verdonik, Kaja Dobrovoljc, Tomaž Erjavec, and Nikola Ljubešić. 2024. Gos 2: A New Reference Corpus of Spoken Slovenian. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7825–7830, Torino, Italia. ELRA and ICCL.