{"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/stranse-a-novel-embedding-model-of-entities","title":"STransE: a novel embedding model of entities and relationships in knowledge bases","arxiv_id":"1606.08140","date":"2016-06-27","proceeding":"NAACL 2016 6","authors":["Dat Quoc Nguyen","Kairit Sirts","Lizhen Qu","Mark Johnson"],"abstract":"Knowledge bases of real-world facts about entities and their relationships\nare useful resources for a variety of natural language processing tasks.\nHowever, because knowledge bases are typically incomplete, it is useful to be\nable to perform link prediction or knowledge base completion, i.e., predict\nwhether a relationship not in the knowledge base is likely to be true. This\npaper combines insights from several previous link prediction models into a new\nembedding model STransE that represents each entity as a low-dimensional\nvector, and each relation by two matrices and a translation vector. STransE is\na simple combination of the SE and TransE models, but it obtains better link\nprediction performance on two benchmark datasets than previous embedding\nmodels. Thus, STransE can serve as a new baseline for the more complex models\nin the link prediction task.","url_abs":"http://arxiv.org/abs/1606.08140v3","url_pdf":"http://arxiv.org/pdf/1606.08140v3.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":"stranse-a-novel-embedding-model-of-entities","repo_url":"https://github.com/datquocnguyen/STransE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"transe","method_name":"TransE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.08140","atlas_url":"https://app.syntology.ai/?focus=1606.08140","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}