{"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/kate-k-competitive-autoencoder-for-text","title":"KATE: K-Competitive Autoencoder for Text","arxiv_id":"1705.02033","date":"2017-05-04","proceeding":null,"authors":["Yu Chen","Mohammed J. Zaki"],"abstract":"Autoencoders have been successful in learning meaningful representations from\nimage datasets. However, their performance on text datasets has not been widely\nstudied. Traditional autoencoders tend to learn possibly trivial\nrepresentations of text documents due to their confounding properties such as\nhigh-dimensionality, sparsity and power-law word distributions. In this paper,\nwe propose a novel k-competitive autoencoder, called KATE, for text documents.\nDue to the competition between the neurons in the hidden layer, each neuron\nbecomes specialized in recognizing specific data patterns, and overall the\nmodel can learn meaningful representations of textual data. A comprehensive set\nof experiments show that KATE can learn better representations than traditional\nautoencoders including denoising, contractive, variational, and k-sparse\nautoencoders. Our model also outperforms deep generative models, probabilistic\ntopic models, and even word representation models (e.g., Word2Vec) in terms of\nseveral downstream tasks such as document classification, regression, and\nretrieval.","url_abs":"http://arxiv.org/abs/1705.02033v2","url_pdf":"http://arxiv.org/pdf/1705.02033v2.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":"kate-k-competitive-autoencoder-for-text","repo_url":"https://github.com/hugochan/KATE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"topic-models","task_name":"Topic Models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.02033","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}