A topic-wise contrastive regularizer using precomputed NPMI similarities improves coherence and diversity of neural topic model topics on 20NG, Yahoo, and NYTimes.
Is automated topic model evaluation broken? the incoherence of coherence,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning
A topic-wise contrastive regularizer using precomputed NPMI similarities improves coherence and diversity of neural topic model topics on 20NG, Yahoo, and NYTimes.