{"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/global-relation-embedding-for-relation","title":"Global Relation Embedding for Relation Extraction","arxiv_id":"1704.05958","date":"2017-04-19","proceeding":"NAACL 2018 6","authors":["Yu Su","Honglei Liu","Semih Yavuz","Izzeddin Gur","Huan Sun","Xifeng Yan"],"abstract":"We study the problem of textual relation embedding with distant supervision.\nTo combat the wrong labeling problem of distant supervision, we propose to\nembed textual relations with global statistics of relations, i.e., the\nco-occurrence statistics of textual and knowledge base relations collected from\nthe entire corpus. This approach turns out to be more robust to the training\nnoise introduced by distant supervision. On a popular relation extraction\ndataset, we show that the learned textual relation embedding can be used to\naugment existing relation extraction models and significantly improve their\nperformance. Most remarkably, for the top 1,000 relational facts discovered by\nthe best existing model, the precision can be improved from 83.9% to 89.3%.","url_abs":"http://arxiv.org/abs/1704.05958v2","url_pdf":"http://arxiv.org/pdf/1704.05958v2.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":"global-relation-embedding-for-relation","repo_url":"https://github.com/ppuliu/GloRE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"global-relation-embedding-for-relation","repo_url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/glore_res","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.05958","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}