{"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/interpreting-embedding-models-of-knowledge","title":"Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach","arxiv_id":"1806.09504","date":"2018-06-20","proceeding":null,"authors":["Arthur Colombini Gusmão","Alvaro Henrique Chaim Correia","Glauber De Bona","Fabio Gagliardi Cozman"],"abstract":"Knowledge bases are employed in a variety of applications from natural\nlanguage processing to semantic web search; alas, in practice their usefulness\nis hurt by their incompleteness. Embedding models attain state-of-the-art\naccuracy in knowledge base completion, but their predictions are notoriously\nhard to interpret. In this paper, we adapt \"pedagogical approaches\" (from the\nliterature on neural networks) so as to interpret embedding models by\nextracting weighted Horn rules from them. We show how pedagogical approaches\nhave to be adapted to take upon the large-scale relational aspects of knowledge\nbases and show experimentally their strengths and weaknesses.","url_abs":"http://arxiv.org/abs/1806.09504v1","url_pdf":"http://arxiv.org/pdf/1806.09504v1.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":"interpreting-embedding-models-of-knowledge","repo_url":"https://github.com/arthurcgusmao/XKE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}