A roadmap to neural automatic post-editing: an empirical approach
Open Access
- 3 September 2020
- journal article
- research article
- Published by Springer Nature in Machine Translation
- Vol. 34 (2-3) , 67-96
Abstract
In a translation workflow, machine translation (MT) is almost always followed by a human post-editing step, where the raw MT output is corrected to meet required quality standards. To reduce the number of errors human translators need to correct, automatic post-editing (APE) methods have been developed and deployed in such workflows. With the advances in deep learning, neural APE (NPE) systems have outranked more traditional, statistical, ones. However, the plethora of options, variables and settings, as well as the relation between NPE performance and train/test data makes it difficult to select the most suitable approach for a given use case. In this article, we systematically analyse these different parameters with respect to NPE performance. We build an NPE “roadmap” to trace the different decision points and train a set of systems selecting different options through the roadmap. We also propose a novel approach for APE with data augmentation. We then analyse the performance of 15 of these systems and identify the best ones. In fact, the best systems are the ones that follow the newly-proposed method. The work presented in this article follows from a collaborative project between Microsoft and the ADAPT centre. The data provided by Microsoft originates from phrase-based statistical MT (PBSMT) systems employed in production. All tested NPE systems significantly increase the translation quality, proving the effectiveness of neural post-editing in the context of a commercial translation workflow that leverages PBSMT.Keywords
Funding Information
- Science Foundation Ireland (Grant 13/RC/2106)
- H2020 Marie Sklodowska-Curie Actions (713567)
This publication has 17 references indexed in Scilit:
- Six Challenges for Neural Machine Translation2017
- Findings of the 2017 Conference on Machine Translation (WMT17)2017
- Generating titles for millions of browse pages on an e-Commerce site2017
- CUNI System for WMT17 Automatic Post-Editing Task2017
- Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing2016
- Neural Machine Translation of Rare Words with Subword Units2016
- Improving Neural Machine Translation Models with Monolingual Data2016
- Controlling Politeness in Neural Machine Translation via Side Constraints2016
- Morfessor 2.0: Toolkit for statistical morphological segmentation2014
- Unsupervised Morphology Induction Using MorfessorLecture Notes in Computer Science, 2006