{"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/document-informed-neural-autoregressive-topic","title":"Document Informed Neural Autoregressive Topic Models with Distributional Prior","arxiv_id":"1809.06709","date":"2018-09-15","proceeding":null,"authors":["Pankaj Gupta","Yatin Chaudhary","Florian Buettner","Hinrich Schütze"],"abstract":"We address two challenges in topic models: (1) Context information around\nwords helps in determining their actual meaning, e.g., \"networks\" used in the\ncontexts \"artificial neural networks\" vs. \"biological neuron networks\".\nGenerative topic models infer topic-word distributions, taking no or only\nlittle context into account. Here, we extend a neural autoregressive topic\nmodel to exploit the full context information around words in a document in a\nlanguage modeling fashion. The proposed model is named as iDocNADE. (2) Due to\nthe small number of word occurrences (i.e., lack of context) in short text and\ndata sparsity in a corpus of few documents, the application of topic models is\nchallenging on such texts. Therefore, we propose a simple and efficient way of\nincorporating external knowledge into neural autoregressive topic models: we\nuse embeddings as a distributional prior. The proposed variants are named as\nDocNADEe and iDocNADEe.\n  We present novel neural autoregressive topic model variants that consistently\noutperform state-of-the-art generative topic models in terms of generalization,\ninterpretability (topic coherence) and applicability (retrieval and\nclassification) over 7 long-text and 8 short-text datasets from diverse\ndomains.","url_abs":"http://arxiv.org/abs/1809.06709v2","url_pdf":"http://arxiv.org/pdf/1809.06709v2.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":"document-informed-neural-autoregressive-topic","repo_url":"https://github.com/pgcool/iDocNADEe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"topic-models","task_name":"Topic Models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.06709","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}