Neural Automatic Post-Editing Using Prior Alignment and Reranking

Abstract

We present a second-stage machine translation (MT) system based on a neural machine translation (NMT) approach to automatic post-editing (APE) that improves the translation quality provided by a first-stage MT system. Our APE system (APE\_Sym) is an extended version of an attention based NMT model with bilingual symmetry employing bidirectional models, mt--pe and pe--mt. APE translations produced by our system show statistically significant improvements over the first-stage MT, phrase-based APE and the best reported score on the WMT 2016 APE dataset by a previous neural APE system. Re-ranking (APE\_Rerank) of the n-best translations from the phrase-based APE and APE\_Sym systems provides further substantial improvements over the symmetric neural APE model. Human evaluation confirms that the APE\_Rerank generated PE translations improve on the previous best neural APE system at WMT 2016.

Tasks

Reproductions