Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation
Zihan Liu, Zewei Sun, Shanbo Cheng, Shujian Huang, Mingxuan Wang
- Anthology ID:
- 2023.ijcnlp-main.47
- Volume:
- Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2023
- Address:
- Nusa Dua, Bali
- Editors:
- Jong C. Park, Yuki Arase, Baotian Hu, Wei Lu, Derry Wijaya, Ayu Purwarianti, Adila Alfa Krisnadhi
- Venues:
- IJCNLP | AACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 733–743
- Language:
- URL:
- https://aclanthology.org/2023.ijcnlp-main.47
- DOI:
- Cite (ACL):
- Zihan Liu, Zewei Sun, Shanbo Cheng, Shujian Huang, and Mingxuan Wang. 2023. Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 733–743, Nusa Dua, Bali. Association for Computational Linguistics.
- Cite (Informal):
- Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation (Liu et al., IJCNLP-AACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.ijcnlp-main.47.pdf