Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing
This addresses the problem of unnecessary modifications in APE for translation tasks, offering an incremental improvement with a novel method.
The paper tackled over-correction in Automatic Post-Editing (APE) systems by integrating word-level Quality Estimation (QE) during decoding, resulting in TER gains of 0.65, 1.86, and 1.44 points across three language pairs.
Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, diverging from the principle of minimal editing. In this paper, we propose a novel technique to mitigate over-correction by incorporating word-level Quality Estimation (QE) information during the decoding process. This method is architecture-agnostic, making it adaptable to any APE system, regardless of the underlying model or training approach. Our experiments on English-German, English-Hindi, and English-Marathi language pairs show the proposed approach yields significant improvements over their corresponding baseline APE systems, with TER gains of $0.65$, $1.86$, and $1.44$ points, respectively. These results underscore the complementary relationship between QE and APE tasks and highlight the effectiveness of integrating QE information to reduce over-correction in APE systems.