The present article studies translation quality when limited training data is available to translate towards morphologically rich languages. The starting point is a neural MT system, used to train translation models with only publicly available parallel data. An initial analysis of the translation output has shown that quality is sub-optimal, mainly due to the insufficient amount of training data. To improve translation, a hybridized solution is proposed, using an ensemble of relatively simple NMT systems trained with different metrics, combined with an open source module designed for low-resource MT that measures the alignment level. A quantitative analysis based on established metrics is complemented by a qualitative analysis of translation results. These show that over multiple test sets, the proposed hybridized method confers improvements over (ⅰ) both the best individual NMT and (ⅱ) the ensemble system provided in the Marian-NMT package. Improvements over Marian-NMT are in many cases statistically significant.
展开▼
