{"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/mixing-dirichlet-topic-models-and-word","title":"Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec","arxiv_id":"1605.02019","date":"2016-05-06","proceeding":null,"authors":["Christopher E Moody"],"abstract":"Distributed dense word vectors have been shown to be effective at capturing\ntoken-level semantic and syntactic regularities in language, while topic models\ncan form interpretable representations over documents. In this work, we\ndescribe lda2vec, a model that learns dense word vectors jointly with\nDirichlet-distributed latent document-level mixtures of topic vectors. In\ncontrast to continuous dense document representations, this formulation\nproduces sparse, interpretable document mixtures through a non-negative simplex\nconstraint. Our method is simple to incorporate into existing automatic\ndifferentiation frameworks and allows for unsupervised document representations\ngeared for use by scientists while simultaneously learning word vectors and the\nlinear relationships between them.","url_abs":"http://arxiv.org/abs/1605.02019v1","url_pdf":"http://arxiv.org/pdf/1605.02019v1.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":"mixing-dirichlet-topic-models-and-word","repo_url":"https://github.com/cemoody/lda2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mixing-dirichlet-topic-models-and-word","repo_url":"https://github.com/Arikskigin/Lda2vec_Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"mixing-dirichlet-topic-models-and-word","repo_url":"https://github.com/Wurmloch/TopicModeling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mixing-dirichlet-topic-models-and-word","repo_url":"https://github.com/avinashok/TextCategorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"mixing-dirichlet-topic-models-and-word","repo_url":"https://github.com/folivetti/HBLCoClust","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"topic-models","task_name":"Topic Models"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"lda2vec","method_name":"lda2vec"}],"datasets_introduced":[],"methods_introduced":[{"slug":"lda2vec","name":"lda2vec","full_name":"lda2vec"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.02019","atlas_url":"https://app.syntology.ai/?focus=1605.02019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.02019"}},"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/Wurmloch/TopicModeling","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cemoody/lda2vec","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avinashok/TextCategorization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Arikskigin/Lda2vec_Implementation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/folivetti/HBLCoClust","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"83bf627137adec16","entry":"most_similar","repo":"cemoody/lda2vec","repo_kind":"official","path":"lda2vec/utils.py","file_url":"https://github.com/cemoody/lda2vec/blob/HEAD/lda2vec/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83bf627137adec16"}},{"code_sha256_prefix":"251258002735eed1","entry":"orthogonal_matrix","repo":"cemoody/lda2vec","repo_kind":"official","path":"lda2vec/fake_data.py","file_url":"https://github.com/cemoody/lda2vec/blob/HEAD/lda2vec/fake_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"251258002735eed1"}},{"code_sha256_prefix":"e2c41958cc5dce97","entry":"sample","repo":"cemoody/lda2vec","repo_kind":"official","path":"lda2vec/fake_data.py","file_url":"https://github.com/cemoody/lda2vec/blob/HEAD/lda2vec/fake_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2c41958cc5dce97"}},{"code_sha256_prefix":"858518cc85c49662","entry":"softmax","repo":"cemoody/lda2vec","repo_kind":"official","path":"lda2vec/fake_data.py","file_url":"https://github.com/cemoody/lda2vec/blob/HEAD/lda2vec/fake_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"858518cc85c49662"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}