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

Dynamic Data Selection for Neural Machine Translation

2017-08-02
Marlies van der Wees, Arianna Bisazza, Christof Monz

Abstract

Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of neural machine translation (NMT), we explore in this paper to what extent and how NMT can also benefit from data selection. While state-of-the-art data selection (Axelrod et al., 2011) consistently performs well for PBMT, we show that gains are substantially lower for NMT. Next, we introduce dynamic data selection for NMT, a method in which we vary the selected subset of training data between different training epochs. Our experiments show that the best results are achieved when applying a technique we call gradual fine-tuning, with improvements up to +2.6 BLEU over the original data selection approach and up to +3.1 BLEU over a general baseline.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1708.00712

PDF

https://arxiv.org/pdf/1708.00712


Comments

Content