Handling Syntactic Divergence in Low-resource Machine Translation
This addresses the challenge of applying neural machine translation to low-resource language pairs with syntactic divergence, offering an incremental improvement over existing data augmentation methods.
The paper tackles the problem of low-resource machine translation for syntactically divergent languages by proposing a method that reorders target-language sentences to match source order for additional training supervision, resulting in significant improvements over semi-supervised alternatives in experiments with Japanese-to-English and Uyghur-to-English scenarios.
Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make it possible to use monolingual data to help alleviate these issues, but back-translation itself fails in extreme low-resource scenarios, especially for syntactically divergent languages. In this paper, we propose a simple yet effective solution, whereby target-language sentences are re-ordered to match the order of the source and used as an additional source of training-time supervision. Experiments with simulated low-resource Japanese-to-English, and real low-resource Uyghur-to-English scenarios find significant improvements over other semi-supervised alternatives.