{"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/from-random-to-supervised-a-novel-dropout","title":"From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information","arxiv_id":"1808.08149","date":"2018-08-24","proceeding":"CONLL 2018 10","authors":["Hengru Xu","Shen Li","Renfen Hu","Si Li","Sheng Gao"],"abstract":"Dropout is used to avoid overfitting by randomly dropping units from the\nneural networks during training. Inspired by dropout, this paper presents\nGI-Dropout, a novel dropout method integrating with global information to\nimprove neural networks for text classification. Unlike the traditional dropout\nmethod in which the units are dropped randomly according to the same\nprobability, we aim to use explicit instructions based on global information of\nthe dataset to guide the training process. With GI-Dropout, the model is\nsupposed to pay more attention to inapparent features or patterns. Experiments\ndemonstrate the effectiveness of the dropout with global information on seven\ntext classification tasks, including sentiment analysis and topic\nclassification.","url_abs":"http://arxiv.org/abs/1808.08149v3","url_pdf":"http://arxiv.org/pdf/1808.08149v3.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":"from-random-to-supervised-a-novel-dropout","repo_url":"https://gitlab.com/xusong19960424/global_cnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"topic-classification","task_name":"Topic Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}