{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/neural-dynamic-focused-topic-model-1","title":"Neural Dynamic Focused Topic Model","arxiv_id":"2301.10988","date":"2023-01-26","proceeding":null,"authors":["Kostadin Cvejoski","Ramsés J. Sánchez","César Ojeda"],"abstract":"Topic models and all their variants analyse text by learning meaningful representations through word co-occurrences. As pointed out by Williamson et al. (2010), such models implicitly assume that the probability of a topic to be active and its proportion within each document are positively correlated. This correlation can be strongly detrimental in the case of documents created over time, simply because recent documents are likely better described by new and hence rare topics. In this work we leverage recent advances in neural variational inference and present an alternative neural approach to the dynamic Focused Topic Model. Indeed, we develop a neural model for topic evolution which exploits sequences of Bernoulli random variables in order to track the appearances of topics, thereby decoupling their activities from their proportions. We evaluate our model on three different datasets (the UN general debates, the collection of NeurIPS papers, and the ACL Anthology dataset) and show that it (i) outperforms state-of-the-art topic models in generalization tasks and (ii) performs comparably to them on prediction tasks, while employing roughly the same number of parameters, and converging about two times faster. Source code to reproduce our experiments is available online.","url_abs":"https://arxiv.org/abs/2301.10988v1","url_pdf":"https://arxiv.org/pdf/2301.10988v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-dynamic-focused-topic-model-1","repo_url":"https://github.com/cvejoski/Neural-Dynamic-Focused-Topic-Model","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"topic-models","task_name":"Topic Models"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"variational-inference","method_name":"Variational Inference"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.10988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10988"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/cvejoski/Neural-Dynamic-Focused-Topic-Model","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b8b47a7284f684fb","entry":"eval_dataset","repo":"cvejoski/Neural-Dynamic-Focused-Topic-Model","repo_kind":"official","path":"scripts/evaluate/topic_models_evaluate_all.py","file_url":"https://github.com/cvejoski/Neural-Dynamic-Focused-Topic-Model/blob/HEAD/scripts/evaluate/topic_models_evaluate_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8b47a7284f684fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}