conftrace_

model perplexity

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

pre-training stability (1) embedding variability (1) multi-head low-rank attention (1) adversarially regularized autoencoder (1) token embedding (1) medical text generation (1) language model pretraining (1) continuous representation (1) discriminative feature (1) training stability (1)

Papers

Stable Language Model Pre-training by Reducing Embedding Variability EMNLP 2024 Generating Continuous Representations of Medical Texts NAACL 2018