Abstract
In this paper, we describe the Bering Lab’s submission to the WMT 2020 Shared Task on Automatic Post-Editing (APE). First, we propose a cross-lingual Transformer architecture that takes a concatenation of a source sentence and a machine-translated (MT) sentence as an input to generate the post-edited (PE) output. For further improvement, we mask incorrect or missing words in the PE output based on word-level quality estimation and then predict the actual word for each mask based on the fine-tuned cross-lingual language model (XLM-RoBERTa). Finally, to address the over-correction problem, we select the final output among the PE outputs and the original MT sentence based on a sentence-level quality estimation. When evaluated on the WMT 2020 English-German APE test dataset, our system improves the NMT output by -3.95 and +4.50 in terms of TER and BLEU, respectively.- Anthology ID:
- 2020.wmt-1.81
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 772–776
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.81
- DOI:
- Cite (ACL):
- Dongjun Lee. 2020. Cross-Lingual Transformers for Neural Automatic Post-Editing. In Proceedings of the Fifth Conference on Machine Translation, pages 772–776, Online. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Lingual Transformers for Neural Automatic Post-Editing (Lee, WMT 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.81.pdf