A VAE (actually an autoencoder) trained on KJV minus ASV embedding differences separates ASV from other Bible translations by reconstruction error, with an unstable claimed accuracy around 84 percent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Style Extraction on Text Embeddings Using VAE and Parallel Dataset
A VAE (actually an autoencoder) trained on KJV minus ASV embedding differences separates ASV from other Bible translations by reconstruction error, with an unstable claimed accuracy around 84 percent.