Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

Abstract

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.

Accepted for presentation at IWSLT 2016, Seattle

References in corpus (2)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• ADADELTA: An Adaptive Learning Rate Method

Cited by in corpus (10)

• THUMT: An Open Source Toolkit for Neural Machine Translation
• SYSTRAN's Pure Neural Machine Translation Systems
• Bridging Neural Machine Translation and Bilingual Dictionaries
• Neural Machine Translation with Pivot Languages
• Machine-Translation History and Evolution: Survey for Arabic-English Translations
• Context in Neural Machine Translation: A Review of Models and Evaluations
• An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
• Machine Translation at Booking.com: Journey and Lessons Learned
• Look-ahead Attention for Generation in Neural Machine Translation
• Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT