Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
This addresses the deployment readiness of neural machine translation for translation systems, but it is incremental as it builds on existing methods with new data.
The study compared translation quality across 30 directions for phrase-based SMT and neural machine translation, finding that neural machine translation could be used in production based on words-per-second ratios.
In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT. Experiments are performed for the recently published United Nations Parallel Corpus v1.0 and its large six-way sentence-aligned subcorpus. In the second part of the paper we investigate aspects of translation speed, introducing AmuNMT, our efficient neural machine translation decoder. We demonstrate that current neural machine translation could already be used for in-production systems when comparing words-per-second ratios.