Abstract
Although end-to-end neural machine translation (NMT) has achieved remarkable progress in the recent years, the idea of adopting multi-pass decoding mechanism into conventional NMT is not well explored. In this paper, we propose a novel architecture called adaptive multi-pass decoder, which introduces a flexible multi-pass polishing mechanism to extend the capacity of NMT via reinforcement learning. More specifically, we adopt an extra policy network to automatically choose a suitable and effective number of decoding passes, according to the complexity of source sentences and the quality of the generated translations. Extensive experiments on Chinese-English translation demonstrate the effectiveness of our proposed adaptive multi-pass decoder upon the conventional NMT with a significant improvement about 1.55 BLEU.- Anthology ID:
- D18-1048
- 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:
- 523–532
- Language:
- URL:
- https://aclanthology.org/D18-1048
- DOI:
- 10.18653/v1/D18-1048
- Cite (ACL):
- Xinwei Geng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2018. Adaptive Multi-pass Decoder for Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 523–532, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Adaptive Multi-pass Decoder for Neural Machine Translation (Geng et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/D18-1048.pdf