{"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/modeling-relation-paths-for-representation","title":"Modeling Relation Paths for Representation Learning of Knowledge Bases","arxiv_id":"1506.00379","date":"2015-06-01","proceeding":"EMNLP 2015 9","authors":["Yankai Lin","Zhiyuan Liu","Huanbo Luan","Maosong Sun","Siwei Rao","Song Liu"],"abstract":"Representation learning of knowledge bases (KBs) aims to embed both entities\nand relations into a low-dimensional space. Most existing methods only consider\ndirect relations in representation learning. We argue that multiple-step\nrelation paths also contain rich inference patterns between entities, and\npropose a path-based representation learning model. This model considers\nrelation paths as translations between entities for representation learning,\nand addresses two key challenges: (1) Since not all relation paths are\nreliable, we design a path-constraint resource allocation algorithm to measure\nthe reliability of relation paths. (2) We represent relation paths via semantic\ncomposition of relation embeddings. Experimental results on real-world datasets\nshow that, as compared with baselines, our model achieves significant and\nconsistent improvements on knowledge base completion and relation extraction\nfrom text.","url_abs":"http://arxiv.org/abs/1506.00379v2","url_pdf":"http://arxiv.org/pdf/1506.00379v2.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":"modeling-relation-paths-for-representation","repo_url":"https://github.com/Mrlyk423/Relation_Extraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-composition","task_name":"Semantic Composition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.00379","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}