papers AI Learner
The Github is limit! Click to go to the new site.

Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search

2017-08-10
Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, Shahram Khadivi

Abstract

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 translation probabilities and a target language model. Experimental results on German->English news domain and English->Russian e-commerce domain translation tasks show that using phrase-based models in NMT search improves MT quality by up to 2.3% BLEU absolute as compared to a strong NMT baseline.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1708.03271

PDF

https://arxiv.org/pdf/1708.03271


Similar Posts

Comments