Abstract
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism. The proposed model improves over both seq2seq and parsed baselines by over 1 BLEU on the WMT17 English-German task. Further analysis shows that our multi-source syntactic model is able to translate successfully without any parsed input, unlike standard parsed methods. In addition, performance does not deteriorate as much on long sentences as for the baselines.- Anthology ID:
- D18-1327
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2961–2966
- Language:
- URL:
- https://aclanthology.org/D18-1327
- DOI:
- 10.18653/v1/D18-1327
- Cite (ACL):
- Anna Currey and Kenneth Heafield. 2018. Multi-Source Syntactic Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2961–2966, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Source Syntactic Neural Machine Translation (Currey & Heafield, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/D18-1327.pdf