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 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
A Hybrid Approach For Hindi-English Machine Translation
In this paper, an extended combined approach of phrase based statistical machine translation (SMT), example based MT (EBMT) and rule based MT (RBMT) is proposed to develop a novel hybrid data driven MT system capable of …
Machine TranslationTranslationCan Machine Learning Algorithms Improve Phrase Selection in Hybrid Machine Translation?
Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation
Recently, the neural machine translation systems showed their promising performance and surpassed the phrase-based systems for most translation tasks. Retreating into conventional concepts machine translation while utili…
Machine TranslationTranslationWord Alignment