Open access
Oct 2026
Semantic Representations based on Neural Topic Models
A Neural Topic Model called ABT is presented which leverages semantic vector spaces (derived from language models) to uncover latent semantic representations in text collections to explore the themes covered by a given textual collection and analyze them as a hierarchical structure of topics.
Fagner Leal Pantoja, A. Santanchè, C. B. Medeiros
· Journal of universal compute... · 0 citations