Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention - researchr publication

researchr

You are not signed in
Sign in
Sign up

Philipp Dufter, Martin Schmitt, Hinrich Schütze. Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention. In Donia Scott, Núria Bel, Chengqing Zong, editors, Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020. pages 3630-3636, International Committee on Computational Linguistics, 2020. [doi]

Abstract is missing.

runs on WebDSL