Skip to content
conftrace_

softmax bottleneck

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

language model (5) mixture of softmax (2) neural network (2) word embedding (2) recurrent neural network (2) language modeling (2) matrix factorization (2) log probability matrice (1) multi-facet softmax (1) logit space vector gating (1)

Papers

Closing the Curious Case of Neural Text Degeneration ICLR 2024 Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions ACL 2022 On the Softmax Bottleneck of Recurrent Language Models AAAI 2021 Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities ICML 2019 Mixtape: Breaking the Softmax Bottleneck Efficiently NeurIPS 2019 Breaking the Softmax Bottleneck: A High-Rank RNN Language Model ICLR 2018