Methods › Natural Language Processing › Topic Embeddings › Contextualized Topic Models
Contextualized Topic Models
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Contextualized Topic Models are based on the Neural-ProdLDA variational autoencoding approach by Srivastava and Sutton (2017).
This approach trains an encoding neural network to map pre-trained contextualized word embeddings (e.g., BERT) to latent representations. Those latent representations are sampled variationally from a Gaussian distribution N(μ, σ²) and passed to a decoder network that has to reconstruct the document bag-of-word representation.
Papers archive 2025-07-28
7 shown of 7, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
BERTopic: Neural topic modeling with a class-based TF-IDF procedure 11 Mar 2022 · 3 repositories · arXiv:2203.05794Syntology ran 1 of 8 samples · 7 unverified
-
One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization 15 Feb 2022 · 1 repository · arXiv:2202.07631
-
OCTIS: Comparing and Optimizing Topic models is Simple! 19 Apr 2021 · 1 repository
-
Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling 11 Apr 2021 · 1 repository · arXiv:2104.05064
-
ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation 25 Aug 2020 · 1 repository · arXiv:2008.10875
-
Cross-lingual Contextualized Topic Models with Zero-shot Learning 16 Apr 2020 · 2 repositories · arXiv:2004.07737Syntology ran 0 of 7 samples · 7 unverified
-
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence 8 Apr 2020 · 3 repositories · arXiv:2004.03974Syntology ran 0 of 1 samples · 1 unverified
Tasks archive 2025-07-28
20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections