{"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/adaptive-scaling-for-sparse-detection-in","title":"Adaptive Scaling for Sparse Detection in Information Extraction","arxiv_id":"1805.00250","date":"2018-05-01","proceeding":"ACL 2018 7","authors":["Hongyu Lin","Yaojie Lu","Xianpei Han","Le Sun"],"abstract":"This paper focuses on detection tasks in information extraction, where\npositive instances are sparsely distributed and models are usually evaluated\nusing F-measure on positive classes. These characteristics often result in\ndeficient performance of neural network based detection models. In this paper,\nwe propose adaptive scaling, an algorithm which can handle the positive\nsparsity problem and directly optimize over F-measure via dynamic\ncost-sensitive learning. To this end, we borrow the idea of marginal utility\nfrom economics and propose a theoretical framework for instance importance\nmeasuring without introducing any additional hyper-parameters. Experiments show\nthat our algorithm leads to a more effective and stable training of neural\nnetwork based detection models.","url_abs":"http://arxiv.org/abs/1805.00250v2","url_pdf":"http://arxiv.org/pdf/1805.00250v2.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":"adaptive-scaling-for-sparse-detection-in","repo_url":"https://github.com/zjjhuihui/bert-adaptive-scaling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.00250","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}