mlsanityData to 14 Oct 2026

Low-Resource Neural Machine Translation for Southern African Languages

arXiv 2104.00366 ↗First posted 1 Apr 2021cs.CL cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

17 of 33 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  5. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  6. 2015Attention-Based Models for Speech Recognitioncited by 401
  7. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  8. 2016Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanismcited by 117
  9. 2015Multi-task Sequence to Sequence Learningcited by 94
  10. 2018Universal Neural Machine Translation for Extremely Low Resource Languagescited by 66
  11. 2017Transfer Learning across Low-Resource, Related Languages for Neural Machine Translationcited by 58
  12. 2020Masakhane -- Machine Translation For Africacited by 49
5 more
  1. 2016Zero-Resource Translation with Multi-Lingual Neural Machine Translationcited by 46
  2. 2014Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentationcited by 14
  3. 2019Benchmarking Neural Machine Translation for Southern African Languagescited by 9
  4. 2018Towards Neural Machine Translation for African Languagescited by 7
  5. 2017Effective Strategies in Zero-Shot Neural Machine Translationcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 2.

7 papers.

  1. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  2. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 98
  3. 2022MMTAfrica: Multilingual Machine Translation for African Languagescited by 11
  4. 2022Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translationcited by 5
  5. 2023Building a Parallel Corpus and Training Translation Models Between Luganda and Englishcited by 3
  6. 2023Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswaticited by 2
  7. 2022Bootstrapping NLP tools across low-resourced African languages: an overview and prospectscited by 0