Low Resource Neural Machine Translation: A Benchmark for Five African Languages

TL;DR

This paper benchmarks neural machine translation for five African low-resource languages, demonstrating that multilingual models significantly improve translation quality and providing standardized datasets for future research.

Contribution

It introduces a comprehensive benchmark for NMT on five African low-resource languages and evaluates various modeling approaches, highlighting the effectiveness of multilingual models.

Findings

Multilingual models improve BLEU scores by up to 5 points.

Significant performance gains observed in low-resource language translation.

Standardized datasets released for future research.

Abstract

Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo, Somali [SATOS]). We collected the available resources on the SATOS languages to evaluate the current state of NMT for LRLs. Our evaluation, comparing a baseline single language pair NMT model against semi-supervised learning, transfer learning, and multilingual modeling, shows significant performance improvements both in the En-LRL and LRL-En directions. In terms of averaged BLEU score, the multilingual approach shows the largest gains, up to +5 points, in six out of ten translation directions. To demonstrate the generalization capability of each model, we also report results on multi-domain test sets. We release the standardized experimental data and the test sets for future works addressing the challenges of NMT in under-resourced settings, in particular for the SATOS languages.