Skip to content
Open access

A Data-Efficient Multilingual Neural Machine Translation Model for Low-Resource Indic Languages

Aug 2026 · Engineering, Technology & Applied Science Research · 0 citations · 22 references

TL;DR

The effectiveness of multilingual transfer learning in low-resource settings is demonstrated by the fine-tuned Multilingual Bidirectional and Auto-Regressive Transformer-50 model, significantly outperforming the pretrained baseline.

Abstract

Low-resource languages face significant challenges in Machine Translation (MT) due to the scarcity of high-quality parallel datasets. This study presents a low-resource language translation system using a multilingual Neural Machine Translation (NMT) approach. The proposed system employs the Multilingual Bidirectional and Auto-Regressive Transformer-50 (mBART-50) model. mBART-50 is a transformer-based multilingual architecture, fine-tuned on the Samanantar dataset to enhance translation quality for Indic languages. English–Tamil and English–Telugu translations are the primary experimental focus, in which cross-lingual transfer learning is leveraged to improve performance despite data scarcity. Model performance is evaluated using the Bilingual Evaluation Understudy (BLEU) score, which demonstrates an improvement over the pretrained baseline model. The mBART-50 is designed to be multilingual to enable its easy generalization to other low-resource Indic languages. This study extends previous research by assessing the effectiveness of multilingual transfer under the low-resource conditions of Indic languages. The fine-tuned model achieves BLEU scores of 45.91 for English–Tamil and 31.23 for English–Telugu, significantly outperforming the pretrained baseline. These results demonstrate the effectiveness of multilingual transfer learning in low-resource settings.

Read PDF

Similar papers

Preprint Aug 2026

Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study

This paper proposes a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol for MNMT models, and reduces the vocabulary size from over 128,000 to approximately 10,000 tokens, enabling a 60% memory saving without any loss in performance.

Ahmed Amine Aliane, N. Semmar, H. Aliane · 0 citations
Open access Jul 2026

Development of a Transformer-Based Neural Machine Translation System for English to Ebira Language

Transformer-based neural machine translation (NMT) models have boosted translation accuracy for high-resource languages; however, research has largely bypassed unwritten and low-resource languages, particularly African languages such as Ebira. Ebira is an unwritten, low-resource language spoken by approximately 2.5 million people predominantly in Kogi State, Nigeria. Existing Ebira machine translation (MT) systems suffer from poor fluency, accuracy, and missed nuances, constrained by small datasets and rule-based methods. This study presents the development of a neural machine translation (NMT) system for English-to-Ebira translation using Google’s T5-base transformer model. A bilingual parallel corpus of 32,322 English-Ebira sentence pairs was compiled and used to fine-tune the model. The system achieved a corpus-level BLEU score of 40.95%, with 87% of evaluated sentences scoring 0.5 BLEU or higher, surpassing the prior rule-based system’s threshold result of 81.50%, corresponding to 6.75% relative improvement. Human evaluation by ten native Ebira speakers yielded a mean rating of 8.33/10 for fluency, accuracy, and cultural relevance. This research demonstrated that the application of transfer learning on transformer NMT model significantly improves the quality of (MT) systems; and also provides a foundational step for the development of computational resources for Ebira and supports the broader goal of linguistic inclusivity in artificial intelligence.

Musari Abdulmusawir Tijani, Amina Hassan Abubakar, A. Kana et al. · 0 citations
Open access Jul 2026

Transliteration for Low-Resource Translation in the Age of Large Language Models

Neural machine translation (NMT) systems are widely used, but their performance remains strongly dependent on the availability of large-scale digital corpora, making translation for low-resource languages a persistent challenge. In parallel, large language models (LLMs) have recently emerged as a promising paradigm for multilingual text generation and translation; however, their behavior in low-resource settings remains largely underexplored. The challenge becomes even more acute for historical languages. Chagatai, a historical Turkic literary language of Central Asia with no native speakers, unstable orthography, and parallel data, represents an extreme case of such a condition. This study investigates whether transliteration significantly affects translation performance and how LLM-based and NMT-based systems compare under an extremely low-resource setting. To address these questions, we evaluated four source-text configurations (original Arabic script, expert manual transliteration, LLM-based transliteration, and rule-based Uroman transliteration) for translation into six target languages: Kazakh, English, Uzbek, Uyghur, Turkish, Russian, and Arabic. The results show that manual transliteration consistently yields the best translation performance, while noisy automatic romanization reduces these gains. For model comparison, GPT-4o was assessed alongside two fine-tuned NMT baselines, NLLB and TranslateGemma. The findings further show that LLM-based translation can be competitive with, and in some settings outperform, fine-tuned NMT systems, although this advantage comes with lower interpretability. Overall, these findings show that, for extremely low-resource historical languages written in non-Latin scripts, source-side representation is a decisive factor and may be as important as the choice of translation model itself.

A. Mansurova, Meruert Bekmukhamedova, Bekarys Baibolat et al. · 0 citations
Preprint Aug 2026

Embedding Initialization for Unseen Low-resource Languages in Multilingual NMT: A Case Study on Limbum-English Translation

The results show that multilingual transfer is the dominant factor in extremely low-resource Bantu translation while eliminating the need for heuristic proxy selection, and all systems fail to preserve tonal diacritics, highlighting an open challenge.

Samiratu Ntohsi, Neza David Tuyishimire, Anesu Kafesu et al. · 0 citations
Open access Jul 2026

Croatian Language in the Transition from Neural Machine Translation to Large Language Models

Machine translation (MT) technologies are currently undergoing a paradigm shift, transitioning from specialized Neural Machine Translation (NMT) frameworks to the broader capabilities of Large Language Models (LLMs). This paper examines the current standing of the Croatian language within this technological evolution. While bilingual NMT models often exhibit high precision, multilingual NMT leverage transfer learning to enhance performance for low–resource language pairs, but with lower performance for high–resource ones. Conversely, LLMs—whether general–purpose or fine–tuned for translation— offer superior multilingual proficiency and context awareness. Unlike NMT, LLMs can process extended discourse, such as full paragraphs or documents, leading to significant improvements in coreference resolution and gender agreement. Despite the substantial computational requirements of LLMs, recent optimization techniques allow for smaller, more efficient versions that maintain high output quality. This study evaluates the performance of various NMT and LLM architectures specifically for Croatian from/to English and Spanish using several automatic quality evaluation metrics. The findings demonstrate that open–source models can achieve, and occasionally surpass, the quality of Google Translate, a widely used commercial NMT system. Furthermore, while our evaluation focuses on this specific language triad, the multilingual nature of the analysed systems suggests that open–source models provide high–quality translation capabilities for Croatian across dozens, if not hundreds, of language pairs.

Antoni Oliver, Sergi Álvarez–Vidal · 1 citation
Preprint Aug 2026

Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment -- Is English Enough?

A PMI-based translation metric is proposed, which is less dependent on the target language and correlates strongly with chrF, and finds that CLA with English predicts translation quality comparably to or better than source-target CLA.

Adnan Al Ali, Kathy Hämmerl, Jindrich Libovický et al. · 0 citations