Learning to Copy for Automatic Post-Editing

Abstract

Automatic post-editing (APE), which aims to correct errors in the output of machine translation systems in a post-processing step, is an important task in natural language processing. While recent work has achieved considerable performance gains by using neural networks, how to model the copying mechanism for APE remains a challenge. In this work, we propose a new method for modeling copying for APE. To better identify translation errors, our method learns the representations of source sentences and system outputs in an interactive way. These representations are used to explicitly indicate which words in the system outputs should be copied, which is useful to help CopyNet (Gu et al., 2016) better generate post-edited translations. Experiments on the datasets of the WMT 2016-2017 APE shared tasks show that our approach outperforms all best published results.

Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation

“…• Flat-Copy is a novel copy mechanism to perform automatic post-editing (APE) proposed by Huang et al (2019). Note that APE focuses on copying from a draft generated by a pre-trained NMT system.…”

“…Note that APE focuses on copying from a draft generated by a pre-trained NMT system. We first arrange candidates of all source words into a sequence as a draft and then copy this flattened "draft" following Huang et al (2019).…”

“…CopyNet is also widely used in text summarization (See et al, 2017;Zhu et al, 2020), automatic postediting (Huang et al, 2019), grammar correction (Zhao et al, 2019a) and so on.…”

“…From a high-level perspective, our methods share a similar Transformer-based architecture with Huang et al (2019) and Zhu et al (2020). Huang et al (2019) employed CopyNet to copy from a draft generated by a pre-trained NMT system.…”

“…From a high-level perspective, our methods share a similar Transformer-based architecture with Huang et al (2019) and Zhu et al (2020). Huang et al (2019) employed CopyNet to copy from a draft generated by a pre-trained NMT system. Zhu et al (2020) proposed a method that integrates the operation of attending, translating, and summarizing to do cross-lingual summarization.…”