A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

Gonçalo M. Correia, André F. T. Martins


Abstract
Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by complementing human post-edited data with large, artificial data generated through back-translations, a time-consuming process often no easier than training a MT system from scratch. in this paper, we propose an alternative where we fine-tune pre-trained BERT models on both the encoder and decoder of an APE system, exploring several parameter sharing strategies. By only training on a dataset of 23K sentences for 3 hours on a single GPU we obtain results that are competitive with systems that were trained on 5M artificial sentences. When we add this artificial data our method obtains state-of-the-art results.
Anthology ID:
P19-1292
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3050–3056
Language:
URL:
https://aclanthology.org/P19-1292
DOI:
10.18653/v1/P19-1292
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/P19-1292.pdf