Low-Resource Neural Machine Translation for Southern African Languages
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationSentenceTransfer LearningTranslationZero-Shot LearningSimilar Papers 제목 키워드 기반
Benchmarking Neural Machine Translation for Southern African Languages
Unlike major Western languages, most African languages are very low-resourced. Furthermore, the resources that do exist are often scattered and difficult to obtain and discover. As a result, the data and code for existin…
BenchmarkingMachine TranslationTranslationUniversity of Cape Town's WMT22 System: Multilingual Machine Translation for Southern African Languages
The paper describes the University of Cape Town's submission to the constrained track of the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages. Our system is a single multilingual transl…
Machine TranslationTranslationFrom Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation
The linguistic diversity across the African continent presents different challenges and opportunities for machine translation. This study explores the effects of data augmentation techniques in improving translation syst…
Machine TranslationData AugmentationA Focus on Neural Machine Translation for African Languages
African languages are numerous, complex and low-resourced. The datasets required for machine translation are difficult to discover, and existing research is hard to reproduce. Minimal attention has been given to machine …
Machine TranslationTranslationToucan: Many-to-Many Translation for 150 African Language Pairs
We address a notable gap in Natural Language Processing (NLP) by introducing a collection of resources designed to improve Machine Translation (MT) for low-resource languages, with a specific focus on African languages. …
Machine TranslationTranslation