Learning to Copy for Automatic Post-Editing

Xuancheng Huang, Yang Liu, Huanbo Luan, Jingfang Xu, Maosong Sun
11/9/2019
cs.CL

Official code: THUNLP-MT/THUMT (706 stars, BSD-3-Clause, last commit 2022-04-26). 1 more implementation below.

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.

View on arXivView PDF

Code Implementations(2)

THUNLP-MT/THUMTOfficial100%
BSD-3-Clause

An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group

706196PythonJun 20, 20174 years agoBSD-3-Clause
deep-learningmachine-translationneural-machine-translation
THUNLP-MT/L2Copy4APEOfficial100%
BSD-3-Clause

Learning to Copy for Automatic Post-Editing (EMNLP 2019)

114PythonAug 18, 20195 years agoBSD-3-Clause

Similar Papers

On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss

85% match2023

Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data

83% match1 repo2512019

Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation

82% match2024

TranslationCorrect: A Unified Framework for Machine Translation Post-Editing with Predictive Error Assistance

81% match2025

Prompting Neural Machine Translation with Translation Memories

81% match2023

Prediction of Translation Techniques for the Translation Process

81% match2024

Cite this paper

@article{huang2019learning,
  title  = {Learning to Copy for Automatic Post-Editing},
  author = {Xuancheng Huang and Yang Liu and Huanbo Luan and Jingfang Xu and Maosong Sun},
  year   = {2019},
  eprint = {1911.03627},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1911.03627}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1911.03627.svg)](https://codeofpaper.com/paper/1911.03627)

Discussion