Zero-Shot Dual Machine Translation
This addresses the challenge of building translation systems for low-resource languages without parallel data, though it builds incrementally on existing unsupervised and semi-supervised methods.
The paper tackles the problem of low-resource machine translation by proposing a zero-shot dual learning method that uses only monolingual data, achieving performance within 2.2 BLEU points of supervised systems and improvements of 4 to 15 BLEU points across multiple language directions.
Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines zero-shot and dual learning. The latter relies on reinforcement learning, to exploit the duality of the machine translation task, and requires only monolingual data for the target language pair. Experiments show that a zero-shot dual system, trained on English-French and English-Spanish, outperforms by large margins a standard NMT system in zero-shot translation performance on Spanish-French (both directions). The zero-shot dual method approaches the performance, within 2.2 BLEU points, of a comparable supervised setting. Our method can obtain improvements also on the setting where a small amount of parallel data for the zero-shot language pair is available. Adding Russian, to extend our experiments to jointly modeling 6 zero-shot translation directions, all directions improve between 4 and 15 BLEU points, again, reaching performance near that of the supervised setting.