Information Aggregation for Multi-Head Attention with Routing-by-Agreement

Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu


Abstract
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a linear transformation, which may not fully exploit the expressiveness of multi-head attention. In this work, we propose to improve the information aggregation for multi-head attention with a more powerful routing-by-agreement algorithm. Specifically, the routing algorithm iteratively updates the proportion of how much a part (i.e. the distinct information learned from a specific subspace) should be assigned to a whole (i.e. the final output representation), based on the agreement between parts and wholes. Experimental results on linguistic probing tasks and machine translation tasks prove the superiority of the advanced information aggregation over the standard linear transformation.
Anthology ID:
N19-1359
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
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3566–3575
Language:
URL:
https://aclanthology.org/N19-1359
DOI:
10.18653/v1/N19-1359
Bibkey:
Cite (ACL):
Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, and Zhaopeng Tu. 2019. Information Aggregation for Multi-Head Attention with Routing-by-Agreement. 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 3566–3575, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Information Aggregation for Multi-Head Attention with Routing-by-Agreement (Li et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/N19-1359.pdf
Video:
 https://vimeo.com/359701494