{"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/efficient-path-prediction-for-semi-supervised","title":"Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification","arxiv_id":"1902.09347","date":"2019-02-25","proceeding":null,"authors":["Huiru Xiao","Xin Liu","Yangqiu Song"],"abstract":"Hierarchical text classification has many real-world applications. However,\nlabeling a large number of documents is costly. In practice, we can use\nsemi-supervised learning or weakly supervised learning (e.g., dataless\nclassification) to reduce the labeling cost. In this paper, we propose a path\ncost-sensitive learning algorithm to utilize the structural information and\nfurther make use of unlabeled and weakly-labeled data. We use a generative\nmodel to leverage the large amount of unlabeled data and introduce path\nconstraints into the learning algorithm to incorporate the structural\ninformation of the class hierarchy. The posterior probabilities of both\nunlabeled and weakly labeled data can be incorporated with path-dependent\nscores. Since we put a structure-sensitive cost to the learning algorithm to\nconstrain the classification consistent with the class hierarchy and do not\nneed to reconstruct the feature vectors for different structures, we can\nsignificantly reduce the computational cost compared to structural output\nlearning. Experimental results on two hierarchical text classification\nbenchmarks show that our approach is not only effective but also efficient to\nhandle the semi-supervised and weakly supervised hierarchical text\nclassification.","url_abs":"http://arxiv.org/abs/1902.09347v1","url_pdf":"http://arxiv.org/pdf/1902.09347v1.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":"efficient-path-prediction-for-semi-supervised","repo_url":"https://github.com/HKUST-KnowComp/PathPredictionForTextClassification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.09347","atlas_url":"https://app.syntology.ai/?focus=1902.09347","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}