{"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/attention-based-capsule-networks-with-dynamic","title":"Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction","arxiv_id":"1812.11321","date":"2018-12-29","proceeding":"EMNLP 2018 10","authors":["Ningyu Zhang","Shumin Deng","Zhanlin Sun","Xi Chen","Wei zhang","Huajun Chen"],"abstract":"A capsule is a group of neurons, whose activity vector represents the\ninstantiation parameters of a specific type of entity. In this paper, we\nexplore the capsule networks used for relation extraction in a multi-instance\nmulti-label learning framework and propose a novel neural approach based on\ncapsule networks with attention mechanisms. We evaluate our method with\ndifferent benchmarks, and it is demonstrated that our method improves the\nprecision of the predicted relations. Particularly, we show that capsule\nnetworks improve multiple entity pairs relation extraction.","url_abs":"http://arxiv.org/abs/1812.11321v1","url_pdf":"http://arxiv.org/pdf/1812.11321v1.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":"attention-based-capsule-networks-with-dynamic","repo_url":"https://github.com/zjunlp/deepke","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-label-learning","task_name":"Multi-Label Learning"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}