Sparsifying Transformer Models with Trainable Representation Pooling

Michal Pietruszka, Lukasz Borchmann, Lukasz Garncarek. Sparsifying Transformer Models with Trainable Representation Pooling. In Smaranda Muresan, Preslav Nakov, Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. pages 8616-8633, Association for Computational Linguistics, 2022. [doi]

Abstract

Abstract is missing.