{"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/reinforcement-learning-for-relation","title":"Reinforcement Learning for Relation Classification from Noisy Data","arxiv_id":"1808.08013","date":"2018-08-24","proceeding":null,"authors":["Jun Feng","Minlie Huang","Li Zhao","Yang Yang","Xiaoyan Zhu"],"abstract":"Existing relation classification methods that rely on distant supervision\nassume that a bag of sentences mentioning an entity pair are all describing a\nrelation for the entity pair. Such methods, performing classification at the\nbag level, cannot identify the mapping between a relation and a sentence, and\nlargely suffers from the noisy labeling problem. In this paper, we propose a\nnovel model for relation classification at the sentence level from noisy data.\nThe model has two modules: an instance selector and a relation classifier. The\ninstance selector chooses high-quality sentences with reinforcement learning\nand feeds the selected sentences into the relation classifier, and the relation\nclassifier makes sentence level prediction and provides rewards to the instance\nselector. The two modules are trained jointly to optimize the instance\nselection and relation classification processes. Experiment results show that\nour model can deal with the noise of data effectively and obtains better\nperformance for relation classification at the sentence level.","url_abs":"http://arxiv.org/abs/1808.08013v1","url_pdf":"http://arxiv.org/pdf/1808.08013v1.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":"reinforcement-learning-for-relation","repo_url":"https://github.com/JuneFeng/RelationClassification-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"reinforcement-learning-for-relation","repo_url":"https://github.com/unreliableXu/TensorFlow_RLRE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08013","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}