Topic adaptation for machine translation of e-commerce content

MT Summit- 2015/10
Topic adaptation for machine translation of e-commerce content
Prashant Mathur, Marcello Federico, Selçuk Köprü, Shahram Khadivi, Hassan Sawaf
Categories
eBay Authors
Abstract
Topic adaptation for machine translation of e-commerce content
Authors
Prashant Mathur, Marcello Federico, Selçuk Köprü, Shahram Khadivi and Hassan Sawaf 
Publication date
2015/10
Conference
MT Summit
Volume
15
Pages
pp. 270-282

Another publication from the same category: Machine Translation

Copenhagen, Denmark, September 2017

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

Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, Shahram Khadivi

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 ecommerce 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.