Bi-Directional Neural Machine Translation with Synthetic Parallel Data

05/29/2018
by   Xing Niu, et al.
0

Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation. We propose a novel technique that combines back-translation and multilingual NMT to improve performance in these difficult cases. Our technique trains a single model for both directions of a language pair, allowing us to back-translate source or target monolingual data without requiring an auxiliary model. We then continue training on the augmented parallel data, enabling a cycle of improvement for a single model that can incorporate any source, target, or parallel data to improve both translation directions. As a byproduct, these models can reduce training and deployment costs significantly compared to uni-directional models. Extensive experiments show that our technique outperforms standard back-translation in low-resource scenarios, improves quality on cross-domain tasks, and effectively reduces costs across the board.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/30/2019

Handling Syntactic Divergence in Low-resource Machine Translation

Despite impressive empirical successes of neural machine translation (NM...
research
09/09/2021

HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints

Back-translation (BT) of target monolingual corpora is a widely used dat...
research
06/30/2021

Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment

We propose a Bi-Directional Manifold Alignment (BDMA) that learns a non-...
research
11/02/2018

Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation

We aim to better exploit the limited amounts of parallel text available ...
research
01/19/2022

Improving Neural Machine Translation by Denoising Training

We present a simple and effective pretraining strategy Denoising Trainin...
research
09/28/2019

The Source-Target Domain Mismatch Problem in Machine Translation

While we live in an increasingly interconnected world, different places ...
research
04/22/2020

When and Why is Unsupervised Neural Machine Translation Useless?

This paper studies the practicality of the current state-of-the-art unsu...

Please sign up or login with your details

Forgot password? Click here to reset