Democratizing Machine Translation: A CPU-Centric Training Pipeline for Low-Resource Languages (A Kalabari Case Study)

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

The findings show that manual transliteration consistently yields the best translation performance, while noisy automatic romanization reduces these gains, and that LLM-based translation can be competitive with, and in some settings outperform, fine-tuned NMT systems, although this advantage comes with lower interpretability.

Building ‌a ‌Transformer-Based ‌Neural Machine Translation System for English–Kibajuni Translation: A Low-Resource Deep Learning Approach for Indigenous Language Preservation

Recent progress in artificial intelligence has pushed machine translation to high levels of accuracy for widely resourced languages. Yet for many indigenous and endangered languages, comparable tools remain absent, largely because digitized linguistic data are scarce. Kibajuni, a minimally documented Bantu language spoken along the Kenyan coast, illustrates this gap. Publicly accessible English–Kibajuni machine translation systems are not available, which restricts both everyday digital use and broader language preservation work.This paper reports the design, construction, and assessment of a compact Transformer-based Neural Machine Translation (NMT) system for English–Kibajuni translation. Training relied on a community-produced parallel corpus of roughly 10,000 aligned sentence pairs. A Design Science Research approach guided development of the full translation workflow, beginning with corpus preparation and continuing through Byte Pair Encoding (BPE) tokenization, a custom encoder–decoder Transformer, supervised training in PyTorch, beam-search decoding at inference time, and deployment as a web application.Because data were limited, emphasis was placed on training stability and generalization rather than increasing model size. The system therefore integrated AdamW, OneCycle learning-rate scheduling, dropout, label smoothing, gradient clipping, mixed-precision training, and early stopping driven by validation BLEU. Results indicate that, despite the small dataset, the model learned usable semantic correspondences between English and Kibajuni while remaining computationally light. The final network contains about 6–8 million parameters, occupies roughly 27 MB, and supports real-time translation on modest hardware. In practical terms, the work provides one of the earliest operational English–Kibajuni neural translation platforms. At the methodological level, it offers a reproducible template for developing MT systems for other under-resourced African languages. Taken together, the findings suggest that appropriately scaled Transformer models, paired with subword tokenization and carefully tuned training procedures, can materially advance digital inclusion and language preservation for endangered languages. 

Building a Transformer-Based Neural Machine Translation System for English–Kibajuni Translation: A Low-Resource Deep Learning Approach for Indigenous Language Preservation

TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation

This paper introduces *TranslatePsy-AfriSLM*, a collection of open-source MT resources for 19 Sub-Saharan African languages, including curated parallel data, African-specialized synthetic data, and a family of fine-tuned SLMs.

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.

A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books

A pipeline that uses large language models to extract grammatical rules, example sentences, and lexicons from grammar books and generate synthetic parallel corpora for fine-tuning-rather than feeding grammar content into prompts at inference time, as in prior work is introduced.