Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence.

Federico Bianchi Silvia Terragni Dirk Hovy

Published in: ACL/IJCNLP (2) (2021)

Keyphrases

training set
document collections
vector space
topic discovery
information retrieval
document content
keywords
artificial neural networks
co occurrence
semantic information
document images
manifold learning
statistical topic models