Word Representation Models for Morphologically Rich Languages in Neural Machine Translation
This addresses translation challenges for morphologically rich languages, offering incremental improvements over existing methods.
The paper tackles the problem of translating morphologically rich languages by proposing word representation models from character and morpheme decompositions, resulting in consistent improvements of 1 to 1.5 BLEU points over strong baselines.
Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the identity for rare words, in this paper we propose several architectures for learning word representations from character and morpheme level word decompositions. We incorporate these representations in a novel machine translation model which jointly learns word alignments and translations via a hard attention mechanism. Evaluating on translating from several morphologically rich languages into English, we show consistent improvements over strong baseline methods, of between 1 and 1.5 BLEU points.