Projects per year
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.
|Title of host publication||Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers|
|Place of Publication||Berlin, Germany|
|Publisher||Association for Computational Linguistics|
|Number of pages||7|
|Publication status||Published - 7 Aug 2016|
|Event||First Conference on Machine Translation - Berlin, Germany|
Duration: 11 Aug 2016 → 12 Aug 2016
|Conference||First Conference on Machine Translation|
|Period||11/08/16 → 12/08/16|
FingerprintDive into the research topics of 'The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT'. Together they form a unique fingerprint.
- 1 Finished