Modeling Text using the Continuous Space Topic Model with Pre-Trained Word Embeddings

no code implementations • ACL 2021 • Seiichi Inoue, Taichi Aida, Mamoru Komachi, Manabu Asai

In this study, we propose a model that extends the continuous space topic model (CSTM), which flexibly controls word probability in a document, using pre-trained word embeddings.

Document Classification Word Embeddings