Towards the Corpus of Latvian Romani Texts: Deciphering the Manuscripts in Jānis Leimanis' Archive

Natalia Perkova; Kirill Kozhanov

Towards the Corpus of Latvian Romani Texts: Deciphering the Manuscripts in Jānis Leimanis' Archive

Natalia Perkova
, Kirill Kozhanov

Finskugriska och nordiska avdelningen

Forskningsoutput: Tidskriftsbidrag › Konferensartikel › Vetenskaplig › Peer review

Sammanfattning

Latvian Romani is a Northeastern Romani dialect with a limited number of publicly available sources. Two large archival collections of texts in Latvian Romani, compiled primarily in the 1930s in Latvia and Estonia, have been recently digitized as images and made available online for a wider public. In our study, we focus on one of these collections, the Latvian Romani folklore texts collected by Jānis Leimanis in interwar Latvia. In this paper, we describe how initial manual transcriptions, most of which have been created with the help of a special crowdsourcing platform, were integrated in the handwritten text recognition (HTR) workflow in Transkribus. We present two HTR models trained on the basis of Leimanis' collection and discuss various issues related to the work on these texts.

Originalspråk	engelska
Tidskrift	CEUR Workshop Proceedings
Volym	3232
Sidor (från-till)	381-389
Antal sidor	9
ISSN	1613-0073
Status	Publicerad - 2022
MoE-publikationstyp	A4 Artikel i en konferenspublikation
Evenemang	6th Digital Humanities in the Nordic and Baltic Countries Conference, DHNB 2022 - Uppsala, Sverige Varaktighet: 15 mars 2022 → 18 mars 2022

Bibliografisk information

Publisher Copyright:
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

Vetenskapsgrenar

6122 Litteraturforskning
6121 Språkvetenskaper
113 Data- och informationsvetenskap

Åtkomst av dokument

paper37Slutlig publicerad version, 1,14 MBLicens: CC BY

https://ceur-ws.org/Vol-3232/paper37.pdfLicens: CC BY

Andra filer och länkar

Link to publication in Scopus

Citera det här

@article{86d05a5f404649c590e9457df68df73e,

title = "Towards the Corpus of Latvian Romani Texts: Deciphering the Manuscripts in Jānis Leimanis' Archive",

abstract = "Latvian Romani is a Northeastern Romani dialect with a limited number of publicly available sources. Two large archival collections of texts in Latvian Romani, compiled primarily in the 1930s in Latvia and Estonia, have been recently digitized as images and made available online for a wider public. In our study, we focus on one of these collections, the Latvian Romani folklore texts collected by Jānis Leimanis in interwar Latvia. In this paper, we describe how initial manual transcriptions, most of which have been created with the help of a special crowdsourcing platform, were integrated in the handwritten text recognition (HTR) workflow in Transkribus. We present two HTR models trained on the basis of Leimanis' collection and discuss various issues related to the work on these texts.",

keywords = "Digitization, Folklore Texts, Handwritten Text Recognition, Latvian Romani, Low-resource Languages, 6122 Literature studies, 6121 Languages, 113 Computer and information sciences",

author = "Natalia Perkova and Kirill Kozhanov",

note = "Publisher Copyright: {\textcopyright} 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0); 6th Digital Humanities in the Nordic and Baltic Countries Conference, DHNB 2022 ; Conference date: 15-03-2022 Through 18-03-2022",

year = "2022",

language = "English",

volume = "3232",

pages = "381--389",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - Towards the Corpus of Latvian Romani Texts

T2 - 6th Digital Humanities in the Nordic and Baltic Countries Conference, DHNB 2022

AU - Perkova, Natalia

AU - Kozhanov, Kirill

PY - 2022

Y1 - 2022

N2 - Latvian Romani is a Northeastern Romani dialect with a limited number of publicly available sources. Two large archival collections of texts in Latvian Romani, compiled primarily in the 1930s in Latvia and Estonia, have been recently digitized as images and made available online for a wider public. In our study, we focus on one of these collections, the Latvian Romani folklore texts collected by Jānis Leimanis in interwar Latvia. In this paper, we describe how initial manual transcriptions, most of which have been created with the help of a special crowdsourcing platform, were integrated in the handwritten text recognition (HTR) workflow in Transkribus. We present two HTR models trained on the basis of Leimanis' collection and discuss various issues related to the work on these texts.

AB - Latvian Romani is a Northeastern Romani dialect with a limited number of publicly available sources. Two large archival collections of texts in Latvian Romani, compiled primarily in the 1930s in Latvia and Estonia, have been recently digitized as images and made available online for a wider public. In our study, we focus on one of these collections, the Latvian Romani folklore texts collected by Jānis Leimanis in interwar Latvia. In this paper, we describe how initial manual transcriptions, most of which have been created with the help of a special crowdsourcing platform, were integrated in the handwritten text recognition (HTR) workflow in Transkribus. We present two HTR models trained on the basis of Leimanis' collection and discuss various issues related to the work on these texts.

KW - Digitization

KW - Folklore Texts

KW - Handwritten Text Recognition

KW - Latvian Romani

KW - Low-resource Languages

KW - 6122 Literature studies

KW - 6121 Languages

KW - 113 Computer and information sciences

UR - https://www.scopus.com/pages/publications/85139789371

M3 - Conference article

AN - SCOPUS:85139789371

SN - 1613-0073

VL - 3232

SP - 381

EP - 389

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 15 March 2022 through 18 March 2022

ER -