Linguistic Input Features Improve Neural Machine Translation

WS 2016 Rico SennrichBarry Haddow

Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information. In this paper we show that the strong learning capability of neural MT models does not make linguistic features redundant; they can be easily incorporated to provide further improvements in performance... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Machine Translation WMT2016 English-German Linguistic Input Features BLEU score 28.4 # 3
Machine Translation WMT2016 German-English Linguistic Input Features BLEU score 32.9 # 2