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-persecond ratios.- Anthology ID:
- 2016.iwslt-1.5
- Volume:
- Proceedings of the 13th International Conference on Spoken Language Translation
- Month:
- December 8-9
- Year:
- 2016
- Address:
- Seattle, Washington D.C
- Editors:
- Mauro Cettolo, Jan Niehues, Sebastian Stüker, Luisa Bentivogli, Rolando Cattoni, Marcello Federico
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- International Workshop on Spoken Language Translation
- Note:
- Pages:
- Language:
- URL:
- https://aclanthology.org/2016.iwslt-1.5
- DOI:
- Cite (ACL):
- Marcin Junczys-Dowmunt, Tomasz Dwojak, and Hieu Hoang. 2016. Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions. In Proceedings of the 13th International Conference on Spoken Language Translation, Seattle, Washington D.C. International Workshop on Spoken Language Translation.
- Cite (Informal):
- Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions (Junczys-Dowmunt et al., IWSLT 2016)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2016.iwslt-1.5.pdf
- Code
- additional community code
- Data
- United Nations Parallel Corpus