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

Document-Level Neural Machine Translation with Hierarchical Attention Networks

2018-10-01
Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas, James Henderson

Abstract

Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is integrated in the original NMT architecture as another level of abstraction, conditioning on the NMT model’s own previous hidden states. Experiments show that hierarchical attention significantly improves the BLEU score over a strong NMT baseline with the state-of-the-art in context-aware methods, and that both the encoder and decoder benefit from context in complementary ways.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1809.01576

PDF

https://arxiv.org/pdf/1809.01576


Similar Posts

Comments