{"url":"/sota/topic-models-on-ag-news","task":{"name":"Topic Models","url":"/task/topic-models","note":null},"dataset":{"name":"AG News","url":"/dataset/ag-news"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"A topic model is a type of statistical model for discovering the abstract \"topics\" that occur in a collection of documents. Topic modeling is a frequently used text-mining tool for the discovery of hidden semantic structures in a text body.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["C_v","NPMI"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"C_v":null,"NPMI":null}},"counts":{"rows":6,"rows_with_code":5,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"vONTSS","metrics":{"C_v":"0.49","NPMI":"0.054"},"uses_additional_data":false,"paper_date":"2023-07-03","paper":"/paper/vontss-vmf-based-semi-supervised-neural-topic","paper_url":"https://arxiv.org/abs/2307.01226v2","paper_title":"vONTSS: vMF based semi-supervised neural topic modeling with optimal transport","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"vNVDM","metrics":{"C_v":"0.44","NPMI":"0.028"},"uses_additional_data":false,"paper_date":"2018-08-31","paper":"/paper/spherical-latent-spaces-for-stable","paper_url":"http://arxiv.org/abs/1808.10805v2","paper_title":"Spherical Latent Spaces for Stable Variational Autoencoders","code":"https://github.com/jiacheng-xu/vmf_vae_nlp","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"GSM","metrics":{"C_v":"0.41","NPMI":"0.03"},"uses_additional_data":false,"paper_date":"2017-06-01","paper":"/paper/discovering-discrete-latent-topics-with","paper_url":"http://arxiv.org/abs/1706.00359v2","paper_title":"Discovering Discrete Latent Topics with Neural Variational Inference","code":"https://github.com/YongfeiYan/Neural-Document-Modeling","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ETM","metrics":{"C_v":"0.41","NPMI":"0.02"},"uses_additional_data":false,"paper_date":"2019-07-08","paper":"/paper/topic-modeling-in-embedding-spaces","paper_url":"https://arxiv.org/abs/1907.04907v1","paper_title":"Topic Modeling in Embedding Spaces","code":"https://github.com/adjidieng/ETM","n_code_links":12,"syntology":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"NSTM","metrics":{"C_v":"0.37","NPMI":"-0.04"},"uses_additional_data":false,"paper_date":"2020-08-12","paper":"/paper/neural-sinkhorn-topic-model","paper_url":"https://arxiv.org/abs/2008.13537v3","paper_title":"Neural Topic Model via Optimal Transport","code":"https://github.com/ethanhezhao/NeuralSinkhornTopicModel","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"ProdLDA","metrics":{"C_v":"0.32","NPMI":"-0.22"},"uses_additional_data":false,"paper_date":"2017-03-04","paper":"/paper/autoencoding-variational-inference-for-topic","paper_url":"http://arxiv.org/abs/1703.01488v1","paper_title":"Autoencoding Variational Inference For Topic Models","code":"https://github.com/mind-Lab/octis","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":1}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":23,"n_samples":28,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":5,"n_unverified":23,"n_samples":28,"n_pointer_only_licence":1,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}