papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-04-03
Xing Niu, Weijia Xu, Marine Carpuat

Abstract

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed inputs, obtained by back-translating translation hypotheses into the input language. We leverage differentiable sampling and bi-directional NMT to train models end-to-end, without introducing additional parameters. This approach achieves small but consistent BLEU improvements on four language pairs in both translation directions, and outperforms an alternative differentiable reconstruction strategy based on hidden states.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.01116

PDF

https://arxiv.org/pdf/1811.01116


Comments

Content