Pith. sign in

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

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural topic models have shown improvements in overall coherence. Concurrently, contextual embeddings have advanced the state of the art of neural models in general. In this paper, we combine contextualized representations with neural topic models. We find that our approach produces more meaningful and coherent topics than traditional bag-of-words topic models and recent neural models. Our results indicate that future improvements in language models will translate into better topic models.

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Continual Neural Topic Model

cs.LG · 2025-08-21 · reject · novelty 5.0

CoNTM is an online neural topic model whose global topics are a running average of time-slice topics; the paper's no-forgetting claim is asserted without a forgetting test.

citing papers explorer

Showing 1 of 1 citing paper.

  • Continual Neural Topic Model cs.LG · 2025-08-21 · reject · none · ref 2017 · internal anchor

    CoNTM is an online neural topic model whose global topics are a running average of time-slice topics; the paper's no-forgetting claim is asserted without a forgetting test.