{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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","slug":"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":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["MaartenGr/BERTopic","maartengr/bertopic_evaluation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/one-configuration-to-rule-them-all-towards","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["MilaNLProc/contextualized-topic-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/pre-training-is-a-hot-topic-contextualized","slug":"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":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["MilaNLProc/contextualized-topic-models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":7,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":7,"with_a_code_link":7,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/contextualized-topic-models/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/contextualized-topic-models/papers/ran/1","json":"/method/contextualized-topic-models/papers/ran/1.json","rows":3}],"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":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Contextualized%20Topic%20Models","read_at":"2026-10-05T00:53:58+00:00","query":"Contextualized Topic Models","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Contextualized Topic Models' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Contextualized World Models (ContextWM)","LX Topic","K-Models","SEE-TOPIC","Topic-BERT","SKI models","neural models","Gemini models"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"dbc5f85465a6d4266821d8cbc8e4e0da3ca5f84130cbfb12fabf605a972d31be","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}