@inproceedings{koncha-etal-2024-parallel,
title = "The Parallel Corpus of {R}ussian and Ruska {R}omani Languages",
author = "Koncha, Kirill and
Kukanova, Abina and
Tatiana, Kazakova and
Rozovskaya, Gloria",
editor = "Serikov, Oleg and
Voloshina, Ekaterina and
Postnikova, Anna and
Muradoglu, Saliha and
Le Ferrand, Eric and
Klyachko, Elena and
Vylomova, Ekaterina and
Shavrina, Tatiana and
Tyers, Francis",
booktitle = "Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.fieldmatters-1.1",
doi = "10.18653/v1/2024.fieldmatters-1.1",
pages = "1--5",
abstract = "The paper presents a parallel corpus for the Ruska Romani dialect and Russian language. Ruska Romani is the dialect of Romani language attributed to Ruska Roma, the largest subgroup of Romani people in Russia. The corpus contains the translations of Russian literature into Ruska Romani dialect. The corpus creation involved manual alignment of a small part of translations with original works, fine-tuning a language model on the aligned pairs, and using the fine-tuned model to align the remaining data. Ruska Romani sentences were annotated using a morphological analyzer, with rules crafted for proper nouns and borrowings. The corpus, available in JSON and Russian National Corpus XML formats. It includes 88,742 Russian tokens and 84,635 Ruska Romani tokens, 74,291 of which were grammatically annotated. The corpus could be used for linguistic research, including comparative and diachronic studies, bilingual dictionary creation, stylometry research, and NLP/MT tool development for Ruska Romani.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koncha-etal-2024-parallel">
<titleInfo>
<title>The Parallel Corpus of Russian and Ruska Romani Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kirill</namePart>
<namePart type="family">Koncha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abina</namePart>
<namePart type="family">Kukanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazakova</namePart>
<namePart type="family">Tatiana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gloria</namePart>
<namePart type="family">Rozovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Voloshina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Postnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Le Ferrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Klyachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper presents a parallel corpus for the Ruska Romani dialect and Russian language. Ruska Romani is the dialect of Romani language attributed to Ruska Roma, the largest subgroup of Romani people in Russia. The corpus contains the translations of Russian literature into Ruska Romani dialect. The corpus creation involved manual alignment of a small part of translations with original works, fine-tuning a language model on the aligned pairs, and using the fine-tuned model to align the remaining data. Ruska Romani sentences were annotated using a morphological analyzer, with rules crafted for proper nouns and borrowings. The corpus, available in JSON and Russian National Corpus XML formats. It includes 88,742 Russian tokens and 84,635 Ruska Romani tokens, 74,291 of which were grammatically annotated. The corpus could be used for linguistic research, including comparative and diachronic studies, bilingual dictionary creation, stylometry research, and NLP/MT tool development for Ruska Romani.</abstract>
<identifier type="citekey">koncha-etal-2024-parallel</identifier>
<identifier type="doi">10.18653/v1/2024.fieldmatters-1.1</identifier>
<location>
<url>https://aclanthology.org/2024.fieldmatters-1.1</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1</start>
<end>5</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Parallel Corpus of Russian and Ruska Romani Languages
%A Koncha, Kirill
%A Kukanova, Abina
%A Tatiana, Kazakova
%A Rozovskaya, Gloria
%Y Serikov, Oleg
%Y Voloshina, Ekaterina
%Y Postnikova, Anna
%Y Muradoglu, Saliha
%Y Le Ferrand, Eric
%Y Klyachko, Elena
%Y Vylomova, Ekaterina
%Y Shavrina, Tatiana
%Y Tyers, Francis
%S Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F koncha-etal-2024-parallel
%X The paper presents a parallel corpus for the Ruska Romani dialect and Russian language. Ruska Romani is the dialect of Romani language attributed to Ruska Roma, the largest subgroup of Romani people in Russia. The corpus contains the translations of Russian literature into Ruska Romani dialect. The corpus creation involved manual alignment of a small part of translations with original works, fine-tuning a language model on the aligned pairs, and using the fine-tuned model to align the remaining data. Ruska Romani sentences were annotated using a morphological analyzer, with rules crafted for proper nouns and borrowings. The corpus, available in JSON and Russian National Corpus XML formats. It includes 88,742 Russian tokens and 84,635 Ruska Romani tokens, 74,291 of which were grammatically annotated. The corpus could be used for linguistic research, including comparative and diachronic studies, bilingual dictionary creation, stylometry research, and NLP/MT tool development for Ruska Romani.
%R 10.18653/v1/2024.fieldmatters-1.1
%U https://aclanthology.org/2024.fieldmatters-1.1
%U https://doi.org/10.18653/v1/2024.fieldmatters-1.1
%P 1-5
Markdown (Informal)
[The Parallel Corpus of Russian and Ruska Romani Languages](https://aclanthology.org/2024.fieldmatters-1.1) (Koncha et al., FieldMatters-WS 2024)
ACL
- Kirill Koncha, Abina Kukanova, Kazakova Tatiana, and Gloria Rozovskaya. 2024. The Parallel Corpus of Russian and Ruska Romani Languages. In Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024), pages 1–5, Bangkok, Thailand. Association for Computational Linguistics.