papers AI Learner
The Github is limit! Click to go to the new site.

Modeling Target-Side Inflection in Neural Machine Translation

2017-09-05
Aleš Tamchyna, Marion Weller-Di Marco, Alexander Fraser

Abstract

NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morphologically rich languages with strong inflectional phenomena. We introduce a simple approach to overcome this problem by training a system to produce the lemma of a word and its morphologically rich POS tag, which is then followed by a deterministic generation step. We apply this strategy for English-Czech and English-German translation scenarios, obtaining improvements in both settings. We furthermore show that the improvement is not due to only adding explicit morphological information.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1707.06012

PDF

https://arxiv.org/pdf/1707.06012


Comments

Content