Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel

Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov


Abstract
Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the attention mechanism, which concurrently processes all inputs in the streams. In this paper, we present a new formulation of attention via the lens of the kernel. To be more precise, we realize that the attention can be seen as applying kernel smoother over the inputs with the kernel scores being the similarities between inputs. This new formulation gives us a better way to understand individual components of the Transformer’s attention, such as the better way to integrate the positional embedding. Another important advantage of our kernel-based formulation is that it paves the way to a larger space of composing Transformer’s attention. As an example, we propose a new variant of Transformer’s attention which models the input as a product of symmetric kernels. This approach achieves competitive performance to the current state of the art model with less computation. In our experiments, we empirically study different kernel construction strategies on two widely used tasks: neural machine translation and sequence prediction.
Anthology ID:
D19-1443
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4344–4353
Language:
URL:
https://aclanthology.org/D19-1443
DOI:
10.18653/v1/D19-1443
Bibkey:
Cite (ACL):
Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4344–4353, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel (Tsai et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1443.pdf