@inproceedings{novokshanov-etal-2026-shughni,
title = "{S}hughni Machine Translation Enhanced by Donor Languages",
author = "Novokshanov, Dmitry and
Humonen, Innokentiy S. and
Makarov, Ilya",
editor = "Merchant, Rayyan and
Megerdoomian, Karine",
booktitle = "The Proceedings of the First Workshop on {NLP} and {LLM}s for the {I}ranian Language Family",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.silkroadnlp-1.12/",
pages = "114--120",
ISBN = "979-8-89176-371-5",
abstract = "This paper presents the first machine translation system for Shughni, an extremely lowresource Eastern Iranian language spoken in Tajikistan and Afghanistan. We fine-tune NLLB-200 models and explore auxiliary language selection through typological similarity and ``super-donor'' experiments. Our final Shughni{--}Russian model achieves a chrF++ score of 36.3 (45.7 on BivalTyp data), establishing the first computational translation resource for this language. Beyond reporting system performance, this work demonstrates a practical path toward supporting languages with virtually no prior MT resources. Our demo system with Shughni-Russian- English translation (Russian serves as a pivot language for the Shughni- English pair) is available on Hugging- Face (https://huggingface.co/spaces/Novokshanov/Shughni-Translator)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="novokshanov-etal-2026-shughni">
<titleInfo>
<title>Shughni Machine Translation Enhanced by Donor Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Novokshanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Innokentiy</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Humonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilya</namePart>
<namePart type="family">Makarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rayyan</namePart>
<namePart type="family">Merchant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karine</namePart>
<namePart type="family">Megerdoomian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-371-5</identifier>
</relatedItem>
<abstract>This paper presents the first machine translation system for Shughni, an extremely lowresource Eastern Iranian language spoken in Tajikistan and Afghanistan. We fine-tune NLLB-200 models and explore auxiliary language selection through typological similarity and “super-donor” experiments. Our final Shughni–Russian model achieves a chrF++ score of 36.3 (45.7 on BivalTyp data), establishing the first computational translation resource for this language. Beyond reporting system performance, this work demonstrates a practical path toward supporting languages with virtually no prior MT resources. Our demo system with Shughni-Russian- English translation (Russian serves as a pivot language for the Shughni- English pair) is available on Hugging- Face (https://huggingface.co/spaces/Novokshanov/Shughni-Translator).</abstract>
<identifier type="citekey">novokshanov-etal-2026-shughni</identifier>
<location>
<url>https://aclanthology.org/2026.silkroadnlp-1.12/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>114</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shughni Machine Translation Enhanced by Donor Languages
%A Novokshanov, Dmitry
%A Humonen, Innokentiy S.
%A Makarov, Ilya
%Y Merchant, Rayyan
%Y Megerdoomian, Karine
%S The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-371-5
%F novokshanov-etal-2026-shughni
%X This paper presents the first machine translation system for Shughni, an extremely lowresource Eastern Iranian language spoken in Tajikistan and Afghanistan. We fine-tune NLLB-200 models and explore auxiliary language selection through typological similarity and “super-donor” experiments. Our final Shughni–Russian model achieves a chrF++ score of 36.3 (45.7 on BivalTyp data), establishing the first computational translation resource for this language. Beyond reporting system performance, this work demonstrates a practical path toward supporting languages with virtually no prior MT resources. Our demo system with Shughni-Russian- English translation (Russian serves as a pivot language for the Shughni- English pair) is available on Hugging- Face (https://huggingface.co/spaces/Novokshanov/Shughni-Translator).
%U https://aclanthology.org/2026.silkroadnlp-1.12/
%P 114-120
Markdown (Informal)
[Shughni Machine Translation Enhanced by Donor Languages](https://aclanthology.org/2026.silkroadnlp-1.12/) (Novokshanov et al., SilkRoadNLP 2026)
ACL
- Dmitry Novokshanov, Innokentiy S. Humonen, and Ilya Makarov. 2026. Shughni Machine Translation Enhanced by Donor Languages. In The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family, pages 114–120, Rabat, Morocco. Association for Computational Linguistics.