Neural Machine Translation with Supervised Attention

Abstract

The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in aligment accuracy. In this paper, we analyze and explain this issue from the point view of re- ordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the super- vised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.

This paper was submitted into COLING2016 on July 10, and it is under review

References in corpus (2)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• ADADELTA: An Adaptive Learning Rate Method

Cited by in corpus (6)

• An Empirical Study of Spatial Attention Mechanisms in Deep Networks
• Bridging Neural Machine Translation and Bilingual Dictionaries
• Translating Phrases in Neural Machine Translation
• GASL: Guided Attention for Sparsity Learning in Deep Neural Networks
• Towards Neural Machine Translation with Partially Aligned Corpora
• Enriched Annotations for Tumor Attribute Classification from Pathology Reports with Limited Labeled Data