Abstract
The word order between source and target languages significantly influences the translation quality. Preordering can effectively address this problem. Previous preordering methods require a manual feature design, making language dependent design difficult. In this paper, we propose a preordering method with recursive neural networks that learn features from raw inputs. Experiments show the proposed method is comparable to the state-of-the-art method but without a manual feature design.- Anthology ID:
- P18-3004
- Volume:
- Proceedings of ACL 2018, Student Research Workshop
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 21–27
- Language:
- URL:
- https://aclanthology.org/P18-3004
- DOI:
- 10.18653/v1/P18-3004
- Cite (ACL):
- Yuki Kawara, Chenhui Chu, and Yuki Arase. 2018. Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation. In Proceedings of ACL 2018, Student Research Workshop, pages 21–27, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation (Kawara et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/P18-3004.pdf
- Data
- ASPEC