{"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/tired-of-topic-models-clusters-of-pretrained","title":"Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!","arxiv_id":"2004.14914","date":"2020-04-30","proceeding":"EMNLP 2020 11","authors":["Suzanna Sia","Ayush Dalmia","Sabrina J. Mielke"],"abstract":"Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA. The best performing combination for our approach performs as well as classical topic models, but with lower runtime and computational complexity.","url_abs":"https://arxiv.org/abs/2004.14914v2","url_pdf":"https://arxiv.org/pdf/2004.14914v2.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":"tired-of-topic-models-clusters-of-pretrained","repo_url":"https://github.com/adalmia96/Cluster-Analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"topic-models","task_name":"Topic Models"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.14914","atlas_url":"https://app.syntology.ai/?focus=2004.14914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14914"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adalmia96/Cluster-Analysis","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"7200461c5e224001","entry":"Agglo_model","repo":"adalmia96/Cluster-Analysis","repo_kind":"official","path":"code/clustering.py","file_url":"https://github.com/adalmia96/Cluster-Analysis/blob/HEAD/code/clustering.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7200461c5e224001"}},{"code_sha256_prefix":"9de0b7bf06d142cf","entry":"find_words_for_cluster","repo":"adalmia96/Cluster-Analysis","repo_kind":"official","path":"code/clustering.py","file_url":"https://github.com/adalmia96/Cluster-Analysis/blob/HEAD/code/clustering.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9de0b7bf06d142cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}