@inproceedings{izmailova-etal-2026-adapting,
title = "Adapting Multilingual {NMT} to Language Isolates: The Role of Proxy Language Selection and Dialect Handling for Nivkh",
author = "Izmailova, Eleonora and
Sorokin, Alexey and
Grashchenkov, Pavel",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Washington, Jonathan and
Oco, Nathaniel and
Zhao, Xiaobing",
booktitle = "Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages ({L}o{R}es{MT} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loresmt-1.11/",
pages = "127--137",
ISBN = "979-8-89176-366-1",
abstract = "Neural machine translation has achieved remarkable results for high-resource languages, yet language isolates {--} those with no demonstrated genetic relatives {--} remain severely underserved, as they cannot benefit from cross-lingual transfer with related languages. We present the first NMT system for Nivkh, a critically endangered language isolate spoken by fewer than 100 fluent speakers in the Russian Far East. Working with approximately 9.5k parallel sentences {--} expanded through fine-tuned LaBSE sentence alignment {--} we adapt NLLB-200 to Nivkh-Russian translation. Since Nivkh is absent from NLLB{'}s language inventory, we investigate proxy language token selection, comparing six typologically diverse languages: Bashkir, Kazakh, Halh Mongolian, Turkish, Tajik, and French. We find that using any proxy substantially outperforms random token initialization (BLEU 18-19.02 vs. 15.44 for rus{\textrightarrow}niv), confirming the value of proxy-based transfer. However, the choice of which proxy has minimal impact, with all six achieving comparable results despite spanning four language families and two scripts. This suggests that for language isolates, practitioners can select any typologically reasonable proxy without significant performance penalty. We additionally present preliminary experiments on dialect-specific models for Amur and Sakhalin Nivkh. Our findings establish baseline results for future Nivkh NLP research and provide practical guidance for adapting multilingual models to other language isolates."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="izmailova-etal-2026-adapting">
<titleInfo>
<title>Adapting Multilingual NMT to Language Isolates: The Role of Proxy Language Selection and Dialect Handling for Nivkh</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleonora</namePart>
<namePart type="family">Izmailova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Grashchenkov</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>Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</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">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</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">979-8-89176-366-1</identifier>
</relatedItem>
<abstract>Neural machine translation has achieved remarkable results for high-resource languages, yet language isolates – those with no demonstrated genetic relatives – remain severely underserved, as they cannot benefit from cross-lingual transfer with related languages. We present the first NMT system for Nivkh, a critically endangered language isolate spoken by fewer than 100 fluent speakers in the Russian Far East. Working with approximately 9.5k parallel sentences – expanded through fine-tuned LaBSE sentence alignment – we adapt NLLB-200 to Nivkh-Russian translation. Since Nivkh is absent from NLLB’s language inventory, we investigate proxy language token selection, comparing six typologically diverse languages: Bashkir, Kazakh, Halh Mongolian, Turkish, Tajik, and French. We find that using any proxy substantially outperforms random token initialization (BLEU 18-19.02 vs. 15.44 for rus→niv), confirming the value of proxy-based transfer. However, the choice of which proxy has minimal impact, with all six achieving comparable results despite spanning four language families and two scripts. This suggests that for language isolates, practitioners can select any typologically reasonable proxy without significant performance penalty. We additionally present preliminary experiments on dialect-specific models for Amur and Sakhalin Nivkh. Our findings establish baseline results for future Nivkh NLP research and provide practical guidance for adapting multilingual models to other language isolates.</abstract>
<identifier type="citekey">izmailova-etal-2026-adapting</identifier>
<location>
<url>https://aclanthology.org/2026.loresmt-1.11/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>127</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting Multilingual NMT to Language Isolates: The Role of Proxy Language Selection and Dialect Handling for Nivkh
%A Izmailova, Eleonora
%A Sorokin, Alexey
%A Grashchenkov, Pavel
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Zhao, Xiaobing
%S Proceedings for the Ninth Workshop on Technologies for Machine Translation of Low Resource Languages (LoResMT 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-366-1
%F izmailova-etal-2026-adapting
%X Neural machine translation has achieved remarkable results for high-resource languages, yet language isolates – those with no demonstrated genetic relatives – remain severely underserved, as they cannot benefit from cross-lingual transfer with related languages. We present the first NMT system for Nivkh, a critically endangered language isolate spoken by fewer than 100 fluent speakers in the Russian Far East. Working with approximately 9.5k parallel sentences – expanded through fine-tuned LaBSE sentence alignment – we adapt NLLB-200 to Nivkh-Russian translation. Since Nivkh is absent from NLLB’s language inventory, we investigate proxy language token selection, comparing six typologically diverse languages: Bashkir, Kazakh, Halh Mongolian, Turkish, Tajik, and French. We find that using any proxy substantially outperforms random token initialization (BLEU 18-19.02 vs. 15.44 for rus→niv), confirming the value of proxy-based transfer. However, the choice of which proxy has minimal impact, with all six achieving comparable results despite spanning four language families and two scripts. This suggests that for language isolates, practitioners can select any typologically reasonable proxy without significant performance penalty. We additionally present preliminary experiments on dialect-specific models for Amur and Sakhalin Nivkh. Our findings establish baseline results for future Nivkh NLP research and provide practical guidance for adapting multilingual models to other language isolates.
%U https://aclanthology.org/2026.loresmt-1.11/
%P 127-137
Markdown (Informal)
[Adapting Multilingual NMT to Language Isolates: The Role of Proxy Language Selection and Dialect Handling for Nivkh](https://aclanthology.org/2026.loresmt-1.11/) (Izmailova et al., LoResMT 2026)
ACL