A Transformer-Based Multi-Source Automatic Post-Editing System
Santanu Pal, Nico Herbig, Antonio Krüger, Josef van Genabith · 2018
This paper presents our English-German Automatic Post-Editing (APE) system submitted to the APE Task organized at WMT 2018(Chatterjee et al., 2018).The proposed model is an extension of the transformer architecture: two separate self-attention-based encoders encode the machine translation output (mt) and the source (src), followed by a joint encoder that attends over a combination of these two encoded sequences (enc src and enc mt ) for generating the post-edited sentence.We compare this multi-source architecture (i.e, {src, mt} → pe) to a monolingual transformer (i.e., mt → pe) model and an ensemble combining the multi-source {src, mt} → pe and singlesource mt → pe models.For both the PBSMT and the NMT task, the ensemble yields the best results, followed by the multi-source model and last the singlesource approach.Our best model, the ensemble, achieves a BLEU score of 66.16 and 74.22 for the PBSMT and NMT task, respectively.