The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation

TL;DR

This paper analyzes recent advances in neural machine translation architectures, isolates key techniques, and develops hybrid models that outperform existing state-of-the-art methods on benchmark datasets.

Contribution

It introduces the RNMT+ model applying key techniques to RNNs and proposes hybrid architectures combining strengths of different models, achieving superior performance.

Findings

RNMT+ outperforms RNN, CNN, and Transformer models on WMT'14 benchmarks.

Hybrid architectures surpass RNMT+ in translation quality.

Key modeling and training techniques are transferable across architectures.

Abstract

The past year has witnessed rapid advances in sequence-to-sequence (seq2seq) modeling for Machine Translation (MT). The classic RNN-based approaches to MT were first out-performed by the convolutional seq2seq model, which was then out-performed by the more recent Transformer model. Each of these new approaches consists of a fundamental architecture accompanied by a set of modeling and training techniques that are in principle applicable to other seq2seq architectures. In this paper, we tease apart the new architectures and their accompanying techniques in two ways. First, we identify several key modeling and training techniques, and apply them to the RNN architecture, yielding a new RNMT+ model that outperforms all of the three fundamental architectures on the benchmark WMT'14 English to French and English to German tasks. Second, we analyze the properties of each fundamental seq2seq architecture and devise new hybrid architectures intended to combine their strengths. Our hybrid models obtain further improvements, outperforming the RNMT+ model on both benchmark datasets.