Star-Transformer

Qipeng Guo, Xipeng Qiu, Pengfei Liu, Yunfan Shao, Xiangyang Xue, Zheng Zhang


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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/N19-1133.pdf
Supplementary:
 N19-1133.Supplementary.pdf
Code
 dmlc/dgl +  additional community code
Data
CoNLL 2003Penn TreebankSNLISSTSST-5