Abstract
Although Transformer has achieved great successes on many NLP tasks, its heavy structure with fully-connected attention connections leads to dependencies on large training data. In this paper, we present Star-Transformer, a lightweight alternative by careful sparsification. To reduce model complexity, we replace the fully-connected structure with a star-shaped topology, in which every two non-adjacent nodes are connected through a shared relay node. Thus, complexity is reduced from quadratic to linear, while preserving the capacity to capture both local composition and long-range dependency. The experiments on four tasks (22 datasets) show that Star-Transformer achieved significant improvements against the standard Transformer for the modestly sized datasets.- Anthology ID:
- N19-1133
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1315–1325
- Language:
- URL:
- https://aclanthology.org/N19-1133
- DOI:
- 10.18653/v1/N19-1133
- Cite (ACL):
- Qipeng Guo, Xipeng Qiu, Pengfei Liu, Yunfan Shao, Xiangyang Xue, and Zheng Zhang. 2019. Star-Transformer. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1315–1325, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Star-Transformer (Guo et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/N19-1133.pdf
- Code
- dmlc/dgl + additional community code
- Data
- CoNLL 2003, Penn Treebank, SNLI, SST, SST-5