{"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/reasoning-over-rdf-knowledge-bases-using-deep","title":"Reasoning over RDF Knowledge Bases using Deep Learning","arxiv_id":"1811.04132","date":"2018-11-09","proceeding":null,"authors":["Monireh Ebrahimi","Md. Kamruzzaman Sarker","Federico Bianchi","Ning Xie","Derek Doran","Pascal Hitzler"],"abstract":"Semantic Web knowledge representation standards, and in particular RDF and\nOWL, often come endowed with a formal semantics which is considered to be of\nfundamental importance for the field. Reasoning, i.e., the drawing of logical\ninferences from knowledge expressed in such standards, is traditionally based\non logical deductive methods and algorithms which can be proven to be sound and\ncomplete and terminating, i.e. correct in a very strong sense. For various\nreasons, though, in particular, the scalability issues arising from the\never-increasing amounts of Semantic Web data available and the inability of\ndeductive algorithms to deal with noise in the data, it has been argued that\nalternative means of reasoning should be investigated which bear high promise\nfor high scalability and better robustness. From this perspective, deductive\nalgorithms can be considered the gold standard regarding correctness against\nwhich alternative methods need to be tested. In this paper, we show that it is\npossible to train a Deep Learning system on RDF knowledge graphs, such that it\nis able to perform reasoning over new RDF knowledge graphs, with high precision\nand recall compared to the deductive gold standard.","url_abs":"http://arxiv.org/abs/1811.04132v1","url_pdf":"http://arxiv.org/pdf/1811.04132v1.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":"reasoning-over-rdf-knowledge-bases-using-deep","repo_url":"https://github.com/md-k-sarker/KG-Cmpl-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"reasoning-over-rdf-knowledge-bases-using-deep","repo_url":"https://github.com/Monireh2/kg-deductive-reasoner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}