{"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/weakly-supervised-neural-text-classification","title":"Weakly-Supervised Neural Text Classification","arxiv_id":"1809.01478","date":"2018-09-02","proceeding":null,"authors":["Yu Meng","Jiaming Shen","Chao Zhang","Jiawei Han"],"abstract":"Deep neural networks are gaining increasing popularity for the classic text\nclassification task, due to their strong expressive power and less requirement\nfor feature engineering. Despite such attractiveness, neural text\nclassification models suffer from the lack of training data in many real-world\napplications. Although many semi-supervised and weakly-supervised text\nclassification models exist, they cannot be easily applied to deep neural\nmodels and meanwhile support limited supervision types. In this paper, we\npropose a weakly-supervised method that addresses the lack of training data in\nneural text classification. Our method consists of two modules: (1) a\npseudo-document generator that leverages seed information to generate\npseudo-labeled documents for model pre-training, and (2) a self-training module\nthat bootstraps on real unlabeled data for model refinement. Our method has the\nflexibility to handle different types of weak supervision and can be easily\nintegrated into existing deep neural models for text classification. We have\nperformed extensive experiments on three real-world datasets from different\ndomains. The results demonstrate that our proposed method achieves inspiring\nperformance without requiring excessive training data and outperforms baseline\nmethods significantly.","url_abs":"http://arxiv.org/abs/1809.01478v2","url_pdf":"http://arxiv.org/pdf/1809.01478v2.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":"weakly-supervised-neural-text-classification","repo_url":"https://github.com/yumeng5/WeSTClass","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01478","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}