{"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/learning-how-to-active-learn-a-deep","title":"Learning how to Active Learn: A Deep Reinforcement Learning Approach","arxiv_id":"1708.02383","date":"2017-08-08","proceeding":"EMNLP 2017 9","authors":["Meng Fang","Yuan Li","Trevor Cohn"],"abstract":"Active learning aims to select a small subset of data for annotation such\nthat a classifier learned on the data is highly accurate. This is usually done\nusing heuristic selection methods, however the effectiveness of such methods is\nlimited and moreover, the performance of heuristics varies between datasets. To\naddress these shortcomings, we introduce a novel formulation by reframing the\nactive learning as a reinforcement learning problem and explicitly learning a\ndata selection policy, where the policy takes the role of the active learning\nheuristic. Importantly, our method allows the selection policy learned using\nsimulation on one language to be transferred to other languages. We demonstrate\nour method using cross-lingual named entity recognition, observing uniform\nimprovements over traditional active learning.","url_abs":"http://arxiv.org/abs/1708.02383v1","url_pdf":"http://arxiv.org/pdf/1708.02383v1.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":"learning-how-to-active-learn-a-deep","repo_url":"https://github.com/mengf1/PAL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.02383","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}