Smart-Start Decoding for Neural Machine Translation
Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, Ming Zhou
Abstract
Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. More specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.- Anthology ID:
- 2021.naacl-main.312
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3982–3988
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.312
- DOI:
- 10.18653/v1/2021.naacl-main.312
- Cite (ACL):
- Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, and Ming Zhou. 2021. Smart-Start Decoding for Neural Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3982–3988, Online. Association for Computational Linguistics.
- Cite (Informal):
- Smart-Start Decoding for Neural Machine Translation (Yang et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.312.pdf