{"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/incorporating-relation-paths-in-neural","title":"Incorporating Relation Paths in Neural Relation Extraction","arxiv_id":"1609.07479","date":"2016-09-23","proceeding":"EMNLP 2017 9","authors":["Wenyuan Zeng","Yankai Lin","Zhiyuan Liu","Maosong Sun"],"abstract":"Distantly supervised relation extraction has been widely used to find novel\nrelational facts from plain text. To predict the relation between a pair of two\ntarget entities, existing methods solely rely on those direct sentences\ncontaining both entities. In fact, there are also many sentences containing\nonly one of the target entities, which provide rich and useful information for\nrelation extraction. To address this issue, we build inference chains between\ntwo target entities via intermediate entities, and propose a path-based neural\nrelation extraction model to encode the relational semantics from both direct\nsentences and inference chains. Experimental results on real-world datasets\nshow that, our model can make full use of those sentences containing only one\ntarget entity, and achieves significant and consistent improvements on relation\nextraction as compared with baselines. The source code of this paper can be\nobtained from https: //github.com/thunlp/PathNRE.","url_abs":"http://arxiv.org/abs/1609.07479v3","url_pdf":"http://arxiv.org/pdf/1609.07479v3.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":"incorporating-relation-paths-in-neural","repo_url":"https://github.com/thunlp/PathNRE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","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=1609.07479","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}