{"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/texttovec-deep-contextualized-neural","title":"textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior","arxiv_id":"1810.03947","date":"2018-10-09","proceeding":"ICLR 2019 5","authors":["Pankaj Gupta","Yatin Chaudhary","Florian Buettner","Hinrich Schütze"],"abstract":"We address two challenges of probabilistic topic modelling in order to better\nestimate the probability of a word in a given context, i.e., P(word|context):\n(1) No Language Structure in Context: Probabilistic topic models ignore word\norder by summarizing a given context as a \"bag-of-word\" and consequently the\nsemantics of words in the context is lost. The LSTM-LM learns a vector-space\nrepresentation of each word by accounting for word order in local collocation\npatterns and models complex characteristics of language (e.g., syntax and\nsemantics), while the TM simultaneously learns a latent representation from the\nentire document and discovers the underlying thematic structure. We unite two\ncomplementary paradigms of learning the meaning of word occurrences by\ncombining a TM (e.g., DocNADE) and a LM in a unified probabilistic framework,\nnamed as ctx-DocNADE. (2) Limited Context and/or Smaller training corpus of\ndocuments: In settings with a small number of word occurrences (i.e., lack of\ncontext) in short text or data sparsity in a corpus of few documents, the\napplication of TMs is challenging. We address this challenge by incorporating\nexternal knowledge into neural autoregressive topic models via a language\nmodelling approach: we use word embeddings as input of a LSTM-LM with the aim\nto improve the word-topic mapping on a smaller and/or short-text corpus. The\nproposed DocNADE extension is named as ctx-DocNADEe.\n  We present novel neural autoregressive topic model variants coupled with\nneural LMs and embeddings priors that consistently outperform state-of-the-art\ngenerative TMs in terms of generalization (perplexity), interpretability (topic\ncoherence) and applicability (retrieval and classification) over 6 long-text\nand 8 short-text datasets from diverse domains.","url_abs":"http://arxiv.org/abs/1810.03947v4","url_pdf":"http://arxiv.org/pdf/1810.03947v4.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":"texttovec-deep-contextualized-neural","repo_url":"https://github.com/pgcool/textTOvec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"information-extraction","task_name":"Information Extraction"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"topic-models","task_name":"Topic Models"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.03947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.03947"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pgcool/textTOvec","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"be3742a12ff64cb0","entry":"get_vectors_from_matrix","repo":"pgcool/textTOvec","repo_kind":"official","path":"train_model.py","file_url":"https://github.com/pgcool/textTOvec/blob/HEAD/train_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be3742a12ff64cb0"}},{"code_sha256_prefix":"91ccc6a2fdaf30d9","entry":"loadGloveModel","repo":"pgcool/textTOvec","repo_kind":"official","path":"train_model.py","file_url":"https://github.com/pgcool/textTOvec/blob/HEAD/train_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91ccc6a2fdaf30d9"}},{"code_sha256_prefix":"51f9969762b91ea3","entry":"softmax","repo":"pgcool/textTOvec","repo_kind":"official","path":"train_model.py","file_url":"https://github.com/pgcool/textTOvec/blob/HEAD/train_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51f9969762b91ea3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}