Title | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2016 | arXiv: Computation and Language | Rule-based machine translation,Example-based machine translation,Computer science,Evaluation of machine translation,Machine translation,Synchronous context-free grammar,Machine translation software usability,Natural language processing,Transfer-based machine translation,Artificial intelligence,Computer-assisted translation,Machine learning |
DocType | Volume | Citations |
Journal | abs/1610.01108 | 36 |
PageRank | References | Authors |
1.54 | 14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcin Junczys-Dowmunt | 1 | 312 | 24.24 |
Tomasz Dwojak | 2 | 36 | 1.54 |
Hieu Hoang | 3 | 1518 | 68.35 |