{"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/190501959","title":"Relation Discovery with Out-of-Relation Knowledge Base as Supervision","arxiv_id":"1905.01959","date":"2019-04-19","proceeding":"NAACL 2019 6","authors":["Yan Liang","Xin Liu","Jianwen Zhang","Yangqiu Song"],"abstract":"Unsupervised relation discovery aims to discover new relations from a given\ntext corpus without annotated data. However, it does not consider existing\nhuman annotated knowledge bases even when they are relevant to the relations to\nbe discovered. In this paper, we study the problem of how to use\nout-of-relation knowledge bases to supervise the discovery of unseen relations,\nwhere out-of-relation means that relations to discover from the text corpus and\nthose in knowledge bases are not overlapped. We construct a set of constraints\nbetween entity pairs based on the knowledge base embedding and then incorporate\nconstraints into the relation discovery by a variational auto-encoder based\nalgorithm. Experiments show that our new approach can improve the\nstate-of-the-art relation discovery performance by a large margin.","url_abs":"http://arxiv.org/abs/1905.01959v1","url_pdf":"http://arxiv.org/pdf/1905.01959v1.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":"190501959","repo_url":"https://github.com/HKUST-KnowComp/RE-RegDVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}