Low-resource African languages have not fully benefited from the progress in neural machine translation because of a lack of data. Motivated by this challenge we compare zero-shot learning, transfer learning and multilingual learning on three Bantu languages (Shona, isiXhosa and isiZulu) and English. Our main target is English-to-isiZulu translation for which we have just 30,000 sentence pairs, 28% of the average size of our other corpora. We show the importance of language similarity on the performance of English-to-isiZulu transfer learning based on English-to-isiXhosa and English-to-Shona parent models whose BLEU scores differ by 5.2. We then demonstrate that multilingual learning surpasses both transfer learning and zero-shot learning on our dataset, with BLEU score improvements relative to the baseline English-to-isiZulu model of 9.9, 6.1 and 2.0 respectively. Our best model also improves the previous SOTA BLEU score by more than 10.

通过比较零-shot 学习、迁移学习和多语言学习在三种班图语（Shona、IsiXhosa 和IsiZulu）和英语翻译中的表现，我们展示了语言相似性对英语到isiZulu的迁移学习性能的重要性，并证明多语言学习在我们的数据集上优于迁移学习和零-shot 学习，其最佳模型相对于基线英语到isiZulu模型的 BLEU得分提高了9.9、6.1和2.0，同时超过了之前的最佳表现。

面向南部非洲语言的低资源神经机器翻译