Work

Document-Level Neural Machine Translation with Hierarchical Attention Networks

Year: 2018

Type: conference-paper

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.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d18-1325

Authors: Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas, James Henderson

Institutions: École Polytechnique Fédérale de Lausanne, Idiap Research Institute

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: European Commission

Awards: G434337789, Scalable Understanding of Multilingual Media