The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
نویسندگان
چکیده
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 phrasebased system cannot surpass state-of-theart pure neural models. For the RussianEnglish 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.
منابع مشابه
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search
In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT). A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search when the attention of the NMT model focuses on the source words translated by this phrase. Phrases added in this way are scored with the NMT model, but also with SMT features including phrase-level transl...
متن کاملThe AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing
This work describes the AMU-UEdin submission to the WMT 2017 shared task on Automatic Post-Editing. We explore multiple neural architectures adapted for the task of automatic post-editing of machine translation output. We focus on neural end-to-end models that combine both inputsmt and src in a single neural architecture, modeling {mt, src} → pe directly. Apart from that, we investigate the inf...
متن کاملSHEF-Multimodal: Grounding Machine Translation on Images
This paper describes the University of Sheffield’s submission for the WMT16 Multimodal Machine Translation shared task, where we participated in Task 1 to develop German-to-English and Englishto-German statistical machine translation (SMT) systems in the domain of image descriptions. Our proposed systems are standard phrase-based SMT systems based on the Moses decoder, trained only on the provi...
متن کاملParFDA for Instance Selection for Statistical Machine Translation
We build parallel feature decay algorithms (ParFDA) Moses statistical machine translation (SMT) systems for all language pairs in the translation task at the first conference on statistical machine translation (Bojar et al., 2016a) (WMT16). ParFDA obtains results close to the top constrained phrase-based SMT with an average of 2.52 BLEU points difference using significantly less computation for...
متن کاملEdinburgh's Statistical Machine Translation Systems for WMT16
This paper describes the University of Edinburgh’s phrase-based and syntax-based submissions to the shared translation tasks of the ACL 2016 First Conference on Machine Translation (WMT16). We submitted five phrase-based and five syntaxbased systems for the news task, plus one phrase-based system for the biomedical task.
متن کامل