Effective Approaches to Attention-based Neural Machine Translation

TL;DR

This paper explores simple global and local attention mechanisms in neural machine translation, demonstrating significant improvements over previous models and establishing new state-of-the-art results on English-German translation tasks.

Contribution

It introduces and evaluates two straightforward attention architectures, showing their effectiveness and setting new performance benchmarks in NMT.

Findings

Local attention improves BLEU by 5.0 points over non-attentional models.

Ensemble of attention architectures achieves 25.9 BLEU on WMT'15 English-German.

Attention-based models outperform previous systems with reranking.

Abstract

An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has been little work exploring useful architectures for attention-based NMT. This paper examines two simple and effective classes of attentional mechanism: a global approach which always attends to all source words and a local one that only looks at a subset of source words at a time. We demonstrate the effectiveness of both approaches over the WMT translation tasks between English and German in both directions. With local attention, we achieve a significant gain of 5.0 BLEU points over non-attentional systems which already incorporate known techniques such as dropout. Our ensemble model using different attention architectures has established a new state-of-the-art result in the WMT'15 English to German translation task with 25.9 BLEU points, an improvement of 1.0 BLEU points over the existing best system backed by NMT and an n-gram reranker.