Title | ||
---|---|---|
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT. |
Abstract | ||
---|---|---|
This paper describes the AMU-UEDIN submissions to the WMT 2016 shared task on news translation. We explore methods of decode-time integration of attention-based neural translation models with phrase-based statistical machine translation. Efficient batch-algorithms for GPU-querying are proposed and implemented. For English-Russian, our system stays behind the state-of-the-art pure neural models in terms of BLEU. Among restricted systems, manual evaluation places it in the first cluster tied with the pure neural model. For the Russian-English task, our submission achieves the top BLEU result, outperforming the best pure neural system by 1.1 BLEU points and our own phrase-based baseline by 1.6 BLEU. After manual evaluation, this system is the best restricted system in its own cluster. In follow-up experiments we improve results by additional 0.8 BLEU. |
Year | Venue | DocType |
---|---|---|
2016 | WMT | Conference |
Volume | Citations | PageRank |
abs/1605.04809 | 11 | 0.63 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcin Junczys-Dowmunt | 1 | 312 | 24.24 |
Tomasz Dwojak | 2 | 24 | 1.95 |
Rico Sennrich | 3 | 945 | 54.92 |