15883

Attention-based NMT Models as Feature Functions in Phrase-based SMT

Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
Faculty of Mathematics and Computer Science, Adam Mickiewicz University in Poznan
arXiv:1605.04809 [cs.CL], (16 May 2016)

@article{junczys-dowmunt2016amuuedin,

   title={The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT},

   author={Junczys-Dowmunt, Marcin and Dwojak, Tomasz and Sennrich, Rico},

   year={2016},

   month={may},

   archivePrefix={"arXiv"},

   primaryClass={cs.CL}

}

Download Download (PDF)   View View   Source Source   

386

views

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, the phrase-based system cannot surpass state-of-the-art stand-alone neural models. 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. In follow-up experiments we improve these results by additional 0.7 BLEU.
VN:F [1.9.22_1171]
Rating: 5.0/5 (2 votes cast)
Attention-based NMT Models as Feature Functions in Phrase-based SMT, 5.0 out of 5 based on 2 ratings

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: