Skip to content
conftrace_

mixture of softmax

4 papers

Explore in graph

Also known as

MOS

Co-occurring keywords · papers mentioning both

softmax bottleneck (2) neural network (2) neural language model (2) language model (2) machine translation (2) multi-facet softmax (1) logit space vector gating (1) sigmoid tree decomposition (1) vocabulary decomposition (1) neural translation (1)

Papers

Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions ACL 2022 Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation AAAI 2019 Improved Language Modeling by Decoding the Past ACL 2019 Mixtape: Breaking the Softmax Bottleneck Efficiently NeurIPS 2019