@inproceedings{martynov-etal-2026-russian,
title = "{R}ussian Generative Spelling, Punctuation and Capitalization Correction",
author = "Martynov, Nikita and
Astafurov, Danil and
Isaeva, Ulyana and
Maksimov, Ivan Vasil{'}yevich and
Azocar, Joqsan and
Kosenko, Dmitrii and
Fenogenova, Alena",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.773/",
doi = "10.63317/2gv3b9npuo2s",
pages = "9861--9872",
abstract = "This paper presents SAGE, an open-access framework that encloses a set of models specifically designed for the generative correction of spelling, punctuation, and capitalization errors in Russian. The release includes four models, featuring a Russian-English version and a distilled version for easy use and cost-effectiveness. The models are pre-trained using a sequence-to-sequence approach on artificial errors that mimic human mistakes and fine-tuned on annotated multi-domain texts. A set of carefully engineered auxiliary learning objectives is employed during pre-training to enrich the models with additional semantic and syntactic information. Evaluations indicate that SAGE models, despite having a small number of parameters, outperform top-tier multilingual and Russian-specific large language models, including both closed- and open-source options, and are considered state-of-the-art. We release the online demo powered by a single Nvidia A100 80GB GPU as a Web service, which allows to simultaneously test the most advanced SAGE model of 1.7B parameters, its distilled version and the Russian-English SAGE model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martynov-etal-2026-russian">
<titleInfo>
<title>Russian Generative Spelling, Punctuation and Capitalization Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Martynov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danil</namePart>
<namePart type="family">Astafurov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ulyana</namePart>
<namePart type="family">Isaeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vasil’yevich</namePart>
<namePart type="family">Maksimov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joqsan</namePart>
<namePart type="family">Azocar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrii</namePart>
<namePart type="family">Kosenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alena</namePart>
<namePart type="family">Fenogenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents SAGE, an open-access framework that encloses a set of models specifically designed for the generative correction of spelling, punctuation, and capitalization errors in Russian. The release includes four models, featuring a Russian-English version and a distilled version for easy use and cost-effectiveness. The models are pre-trained using a sequence-to-sequence approach on artificial errors that mimic human mistakes and fine-tuned on annotated multi-domain texts. A set of carefully engineered auxiliary learning objectives is employed during pre-training to enrich the models with additional semantic and syntactic information. Evaluations indicate that SAGE models, despite having a small number of parameters, outperform top-tier multilingual and Russian-specific large language models, including both closed- and open-source options, and are considered state-of-the-art. We release the online demo powered by a single Nvidia A100 80GB GPU as a Web service, which allows to simultaneously test the most advanced SAGE model of 1.7B parameters, its distilled version and the Russian-English SAGE model.</abstract>
<identifier type="citekey">martynov-etal-2026-russian</identifier>
<identifier type="doi">10.63317/2gv3b9npuo2s</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.773/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9861</start>
<end>9872</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Russian Generative Spelling, Punctuation and Capitalization Correction
%A Martynov, Nikita
%A Astafurov, Danil
%A Isaeva, Ulyana
%A Maksimov, Ivan Vasil’yevich
%A Azocar, Joqsan
%A Kosenko, Dmitrii
%A Fenogenova, Alena
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F martynov-etal-2026-russian
%X This paper presents SAGE, an open-access framework that encloses a set of models specifically designed for the generative correction of spelling, punctuation, and capitalization errors in Russian. The release includes four models, featuring a Russian-English version and a distilled version for easy use and cost-effectiveness. The models are pre-trained using a sequence-to-sequence approach on artificial errors that mimic human mistakes and fine-tuned on annotated multi-domain texts. A set of carefully engineered auxiliary learning objectives is employed during pre-training to enrich the models with additional semantic and syntactic information. Evaluations indicate that SAGE models, despite having a small number of parameters, outperform top-tier multilingual and Russian-specific large language models, including both closed- and open-source options, and are considered state-of-the-art. We release the online demo powered by a single Nvidia A100 80GB GPU as a Web service, which allows to simultaneously test the most advanced SAGE model of 1.7B parameters, its distilled version and the Russian-English SAGE model.
%R 10.63317/2gv3b9npuo2s
%U https://aclanthology.org/2026.lrec-1.773/
%U https://doi.org/10.63317/2gv3b9npuo2s
%P 9861-9872
Markdown (Informal)
[Russian Generative Spelling, Punctuation and Capitalization Correction](https://aclanthology.org/2026.lrec-1.773/) (Martynov et al., LREC 2026)
ACL
- Nikita Martynov, Danil Astafurov, Ulyana Isaeva, Ivan Vasil’yevich Maksimov, Joqsan Azocar, Dmitrii Kosenko, and Alena Fenogenova. 2026. Russian Generative Spelling, Punctuation and Capitalization Correction. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 9861–9872, Palma de Mallorca, Spain. ELRA Language Resource Association.