Neural automatic post-editing using prior alignment and reranking

Santanu Pal, Sudip Kumar Naskar, Mihaela Vela, Qun Liu, Josef van Genabith

In: 15th EACL Conference. Conference of the European Chapter of the Association for Computational Linguistics (EACL-2017) April 3-7 Valencia Spain 2017.


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 firststage MT system. Our APE system (AP ESym) 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 (AP ERerank) of the n-best translations from the phrase-based APE and AP ESym systems provides further substantial improvements over the symmetric neural APE model.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence