Abstract
This paper presents the Automatic Post-editing (APE) systems submitted by the DFKI-MLT group to the WMT’18 APE shared task. Three monolingual neural sequence-to-sequence APE systems were trained using target-language data only: one using an attentional recurrent neural network architecture and two using the attention-only (transformer) architecture. The training data was composed of machine translated (MT) output used as source to the APE model aligned with their manually post-edited version or reference translation as target. We made use of the provided training sets only and trained APE models applicable to phrase-based and neural MT outputs. Results show better performances reached by the attention-only model over the recurrent one, significant improvement over the baseline when post-editing phrase-based MT output but degradation when applied to neural MT output.- Anthology ID:
- W18-6469
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 836–839
- Language:
- URL:
- https://aclanthology.org/W18-6469
- DOI:
- 10.18653/v1/W18-6469
- Cite (ACL):
- Daria Pylypenko and Raphael Rubino. 2018. DFKI-MLT System Description for the WMT18 Automatic Post-editing Task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 836–839, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- DFKI-MLT System Description for the WMT18 Automatic Post-editing Task (Pylypenko & Rubino, WMT 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-6469.pdf
- Data
- eSCAPE