Neural Automatic Post-Editing Using Prior Alignment and Reranking
Santanu Pal, Sudip Kumar Naskar, Mihaela Vela, Qun Liu, Josef van Genabith
Abstract
We present a second-stage machine translation (MT) system based on a neural machine translation (NMT) approach to automatic post-editing (APE) that improves the translation quality provided by a first-stage MT system. Our APE system (APE_Sym) is an extended version of an attention based NMT model with bilingual symmetry employing bidirectional models, mt–pe and pe–mt. APE translations produced by our system show statistically significant improvements over the first-stage MT, phrase-based APE and the best reported score on the WMT 2016 APE dataset by a previous neural APE system. Re-ranking (APE_Rerank) of the n-best translations from the phrase-based APE and APE_Sym systems provides further substantial improvements over the symmetric neural APE model. Human evaluation confirms that the APE_Rerank generated PE translations improve on the previous best neural APE system at WMT 2016.- Anthology ID:
- E17-2056
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 349–355
- Language:
- URL:
- https://aclanthology.org/E17-2056
- DOI:
- Cite (ACL):
- Santanu Pal, Sudip Kumar Naskar, Mihaela Vela, Qun Liu, and Josef van Genabith. 2017. Neural Automatic Post-Editing Using Prior Alignment and Reranking. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 349–355, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Neural Automatic Post-Editing Using Prior Alignment and Reranking (Pal et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/E17-2056.pdf
- Data
- WMT 2016