Linguistic Input Features Improve Neural Machine Translation

WS 2016  ·  Rico Sennrich, Barry 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. We generalize the embedding layer of the encoder in the attentional encoder--decoder architecture to support the inclusion of arbitrary features, in addition to the baseline word feature. We add morphological features, part-of-speech tags, and syntactic dependency labels as input features to English<->German, and English->Romanian neural machine translation systems. In experiments on WMT16 training and test sets, we find that linguistic input features improve model quality according to three metrics: perplexity, BLEU and CHRF3. An open-source implementation of our neural MT system is available, as are sample files and configurations.

PDF Abstract WS 2016 PDF WS 2016 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
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 # 3

Methods


No methods listed for this paper. Add relevant methods here