English

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

Computation and Language 2020-04-01 v1

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.

Keywords

Cite

@article{arxiv.2003.14402,
  title  = {Low Resource Neural Machine Translation: A Benchmark for Five African Languages},
  author = {Surafel M. Lakew and Matteo Negri and Marco Turchi},
  journal= {arXiv preprint arXiv:2003.14402},
  year   = {2020}
}

Comments

Accepted for AfricaNLP workshop at ICLR 2020

R2 v1 2026-06-23T14:34:14.435Z