An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation
This addresses translation challenges for Tigrinya speakers, but it is incremental as it applies known techniques to a specific low-resource language pair.
The paper tackled the problem of low-resource neural machine translation for English to Tigrinya by exploring back-translation methods, finding that pivoting through a related higher-resource language yields substantial improvements over baselines.
It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, often requiring large amounts of auxiliary data to achieve competitive results. An effective method of generating auxiliary data is back-translation of target language sentences. In this work, we present a case study of Tigrinya where we investigate several back-translation methods to generate synthetic source sentences. We find that in low-resource conditions, back-translation by pivoting through a higher-resource language related to the target language proves most effective resulting in substantial improvements over baselines.