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 |

Paper Details:

Month: November
Year: 2019
Location: Hong Kong, China
Venue: EMNLP |
SIG: SIGDAT

Citations

URL

No Citations Yet