Linguistic Input Features Improve Neural Machine Translation
This work addresses the challenge of enhancing translation quality for users of neural machine translation systems, though it is incremental as it builds on existing attentional encoder-decoder architectures.
The authors tackled the problem of improving neural machine translation by incorporating linguistic features, and found that adding morphological features, part-of-speech tags, and syntactic dependency labels led to improvements in perplexity, BLEU, and CHRF3 scores on WMT16 datasets for English<->German and English->Romanian translations.
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.