Transformer-based Automatic Post-Editing with a Context-Aware Encoding Approach for Multi-Source Inputs

TL;DR

This paper introduces a Transformer-based multi-source Automatic Post-Editing model that effectively incorporates source context into machine translation outputs, leading to improved post-edited results and better alignment capture.

Contribution

The paper proposes a novel Transformer model that internally learns to integrate source context into MT representations for enhanced post-editing performance.

Findings

Significant improvement over baseline systems.

State-of-the-art multi-source APE performance.

Successful capture of word alignments in encoding.

Abstract

Recent approaches to the Automatic Post-Editing (APE) research have shown that better results are obtained by multi-source models, which jointly encode both source (src) and machine translation output (mt) to produce post-edited sentence (pe). Along this trend, we present a new multi-source APE model based on the Transformer. To construct effective joint representations, our model internally learns to incorporate src context into mt representation. With this approach, we achieve a significant improvement over baseline systems, as well as the state-of-the-art multi-source APE model. Moreover, to demonstrate the capability of our model to incorporate src context, we show that the word alignment of the unknown MT system is successfully captured in our encoding results.