{"url":"/method/contextualized-topic-models","slug":"contextualized-topic-models","name":"Contextualized Topic Models","full_name":"Contextualized Topic Models","full_name_withheld":false,"description_markdown":"Contextualized Topic Models are based on the Neural-ProdLDA variational autoencoding approach by Srivastava and Sutton (2017). \r\n\r\nThis approach trains an encoding neural network to map pre-trained contextualized word embeddings (e.g., [BERT](https://paperswithcode.com/method/bert)) to latent representations. Those latent representations are sampled variationally from a Gaussian distribution $N(\\mu, \\sigma^2)$ and passed to a decoder network that has to reconstruct the document bag-of-word representation.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2004.07737v2","title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/MilaNLProc/contextualized-topic-models","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Topic Embeddings","url":"/methods/category/topic-embeddings","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/bertopic-neural-topic-modeling-with-a-class","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","date":"2022-03-11","arxiv_id":"2203.05794","n_code_links":3,"syntology":{"ran":1,"of":8,"unverified":7,"pointer_only":0}},{"paper":"/paper/one-configuration-to-rule-them-all-towards","title":"One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization","date":"2022-02-15","arxiv_id":"2202.07631","n_code_links":1,"syntology":null},{"paper":"/paper/octis-comparing-and-optimizing-topic-models","title":"OCTIS: Comparing and Optimizing Topic models is Simple!","date":"2021-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-encoders-for-improved-monolingual","title":"Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling","date":"2021-04-11","arxiv_id":"2104.05064","n_code_links":1,"syntology":null},{"paper":"/paper/etc-nlg-end-to-end-topic-conditioned-natural","title":"ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation","date":"2020-08-25","arxiv_id":"2008.10875","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-contextualized-topic-models","title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning","date":"2020-04-16","arxiv_id":"2004.07737","n_code_links":2,"syntology":{"ran":0,"of":7,"unverified":7,"pointer_only":0}},{"paper":"/paper/pre-training-is-a-hot-topic-contextualized","title":"Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence","date":"2020-04-08","arxiv_id":"2004.03974","n_code_links":3,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}}],"papers_shown":7,"tasks":[{"task":"/task/topic-models","name":"Topic Models","papers":7},{"task":"/task/bayesian-optimization","name":"Bayesian Optimization","papers":2},{"task":"/task/variational-inference","name":"Variational Inference","papers":2},{"task":"/task/all","name":"All","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/bayesian-optimisation","name":"Bayesian Optimisation","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/clustering","name":"Clustering","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/conditional-text-generation","name":"Conditional Text Generation","papers":1},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":1},{"task":"/task/document-classification","name":"Document Classification","papers":1},{"task":"/task/document-embedding","name":"Document Embedding","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/hyperparameter-optimization","name":"Hyperparameter Optimization","papers":1},{"task":"/task/sentence-embeddings","name":"Sentence Embeddings","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1},{"task":"/task/topic-classification","name":"Topic Classification","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":1}],"tasks_shown":20,"n_tasks":20,"usage_by_year":[{"year":"2020","papers":3},{"year":"2021","papers":2},{"year":"2022","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/contextualized-topic-models"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}