{"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/a-hierarchical-framework-for-relation","title":"A Hierarchical Framework for Relation Extraction with Reinforcement Learning","arxiv_id":"1811.03925","date":"2018-11-09","proceeding":null,"authors":["Ryuichi Takanobu","Tianyang Zhang","Jiexi Liu","Minlie Huang"],"abstract":"Most existing methods determine relation types only after all the entities\nhave been recognized, thus the interaction between relation types and entity\nmentions is not fully modeled. This paper presents a novel paradigm to deal\nwith relation extraction by regarding the related entities as the arguments of\na relation. We apply a hierarchical reinforcement learning (HRL) framework in\nthis paradigm to enhance the interaction between entity mentions and relation\ntypes. The whole extraction process is decomposed into a hierarchy of two-level\nRL policies for relation detection and entity extraction respectively, so that\nit is more feasible and natural to deal with overlapping relations. Our model\nwas evaluated on public datasets collected via distant supervision, and results\nshow that it gains better performance than existing methods and is more\npowerful for extracting overlapping relations.","url_abs":"http://arxiv.org/abs/1811.03925v1","url_pdf":"http://arxiv.org/pdf/1811.03925v1.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":"a-hierarchical-framework-for-relation","repo_url":"https://github.com/truthless11/HRL-RE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-hierarchical-framework-for-relation","repo_url":"https://github.com/AndrewSukhobok95/DL_GraphEntity_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"entity-extraction","task_name":"Entity Extraction using GAN"},{"task_slug":"hierarchical-reinforcement-learning","task_name":"Hierarchical Reinforcement Learning"},{"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":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[{"slug":"nyt11-hrl","name":"NYT11-HRL","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-nyt10-hrl","task":"Relation Extraction","dataset":"NYT10-HRL","model":"HRL","rank_in_archive_order":9,"of":10,"metrics":{"F1":"64.4"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-nyt11-hrl","task":"Relation Extraction","dataset":"NYT11-HRL","model":"HRL","rank_in_archive_order":6,"of":12,"metrics":{"F1":"53.8"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-nyt24","task":"Relation Extraction","dataset":"NYT24","model":"HRLRE","rank_in_archive_order":2,"of":2,"metrics":{"F1":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-nyt29","task":"Relation Extraction","dataset":"NYT29","model":"HRLRE","rank_in_archive_order":3,"of":3,"metrics":{"F1":"64.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.03925","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}