Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

Abstract

There are several approaches for improving neural machine translation for low-resource languages: monolingual data can be exploited via pretraining or data augmentation; parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary. We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a higher-resource language. We test various methods on three artificially restricted translation tasks—English to Estonian (low-resource) and Finnish (high-resource), English to Slovak and Czech, English to Danish and Swedish—and one real-world task, Norwegian to North Sámi and Finnish. The experiments show positive effects especially for scheduled multi-task learning, denoising autoencoder, and subword sampling.

There are several approaches for improving neural machine translation for low-resource languages: monolingual data can be exploited via pretraining or data augmentation; parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary. We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a higher-resource language. We test various methods on three artificially restricted translation tasks-English to Estonian (low-resource) and Finnish (high-resource), English to Slovak and Czech, English to Danish and Swedish-and one real-world task, Norwegian to North Sami and Finnish. The experiments show positive effects especially for scheduled multi-task learning, denoising autoencoder, and subword sampling.