@inproceedings{borisov-etal-2025-low,
title = "Low-resource Machine Translation for Code-switched {K}azakh-{R}ussian Language Pair",
author = "Borisov, Maksim and
Kozhirbayev, Zhanibek and
Malykh, Valentin",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.7/",
doi = "10.18653/v1/2025.naacl-srw.7",
pages = "66--76",
ISBN = "979-8-89176-192-6",
abstract = "Machine translation for low-resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. We present the first code-switching Kazakh-Russian parallel corpus.Additionally, we propose a method to build a machine translation model for code-switched Kazakh-Russian language pair with no labeled data. Our method is basing on generation of synthetic data. This method results in a model beating an existing commercial system by human evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borisov-etal-2025-low">
<titleInfo>
<title>Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maksim</namePart>
<namePart type="family">Borisov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanibek</namePart>
<namePart type="family">Kozhirbayev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>Machine translation for low-resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. We present the first code-switching Kazakh-Russian parallel corpus.Additionally, we propose a method to build a machine translation model for code-switched Kazakh-Russian language pair with no labeled data. Our method is basing on generation of synthetic data. This method results in a model beating an existing commercial system by human evaluation.</abstract>
<identifier type="citekey">borisov-etal-2025-low</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.7</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.7/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>66</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
%A Borisov, Maksim
%A Kozhirbayev, Zhanibek
%A Malykh, Valentin
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F borisov-etal-2025-low
%X Machine translation for low-resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. We present the first code-switching Kazakh-Russian parallel corpus.Additionally, we propose a method to build a machine translation model for code-switched Kazakh-Russian language pair with no labeled data. Our method is basing on generation of synthetic data. This method results in a model beating an existing commercial system by human evaluation.
%R 10.18653/v1/2025.naacl-srw.7
%U https://aclanthology.org/2025.naacl-srw.7/
%U https://doi.org/10.18653/v1/2025.naacl-srw.7
%P 66-76
Markdown (Informal)
[Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair](https://aclanthology.org/2025.naacl-srw.7/) (Borisov et al., NAACL 2025)
ACL
- Maksim Borisov, Zhanibek Kozhirbayev, and Valentin Malykh. 2025. Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 66–76, Albuquerque, USA. Association for Computational Linguistics.