Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Borisov, Maksim, Kozhirbayev, Zhanibek, Malykh, Valentin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910893425557504
author Borisov, Maksim
Kozhirbayev, Zhanibek
Malykh, Valentin
author_facet Borisov, Maksim
Kozhirbayev, Zhanibek
Malykh, Valentin
contents Machine translation for low resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. 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. Additionally, we present the first codeswitching Kazakh-Russian parallel corpus and the evaluation results, which include a model achieving 16.48 BLEU almost reaching an existing commercial system and beating it by human evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20007
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
Borisov, Maksim
Kozhirbayev, Zhanibek
Malykh, Valentin
Computation and Language
Machine Learning
Machine translation for low resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. 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. Additionally, we present the first codeswitching Kazakh-Russian parallel corpus and the evaluation results, which include a model achieving 16.48 BLEU almost reaching an existing commercial system and beating it by human evaluation.
title Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2503.20007