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

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-to-English news domain and English-to-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.
Anthology ID:
D17-1148
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1411–1420
Language:
URL:
https://aclanthology.org/D17-1148
DOI:
10.18653/v1/D17-1148
Bibkey:
Cite (ACL):
Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, and Shahram Khadivi. 2017. Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1411–1420, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search (Dahlmann et al., EMNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/D17-1148.pdf