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

05/16/2016
by   Marcin Junczys-Dowmunt, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2018

Phrase-Based Attentions

Most state-of-the-art neural machine translation systems, despite being ...
research
09/19/2018

NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task

This paper presents the NICT's participation to the WMT18 shared news tr...
research
08/28/2018

The University of Cambridge's Machine Translation Systems for WMT18

The University of Cambridge submission to the WMT18 news translation tas...
research
10/15/2019

Facebook AI's WAT19 Myanmar-English Translation Task Submission

This paper describes Facebook AI's submission to the WAT 2019 Myanmar-En...
research
08/01/2019

JUCBNMT at WMT2018 News Translation Task: Character Based Neural Machine Translation of Finnish to English

In the current work, we present a description of the system submitted to...
research
06/14/2017

Fine-grained human evaluation of neural versus phrase-based machine translation

We compare three approaches to statistical machine translation (pure phr...
research
09/01/2018

Microsoft's Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data

This paper describes the Microsoft submission to the WMT2018 news transl...

Please sign up or login with your details

Forgot password? Click here to reset