{"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/dskg-a-deep-sequential-model-for-knowledge","title":"DSKG: A Deep Sequential Model for Knowledge Graph Completion","arxiv_id":"1810.12582","date":"2018-10-30","proceeding":null,"authors":["Lingbing Guo","Qingheng Zhang","Weiyi Ge","Wei Hu","Yuzhong Qu"],"abstract":"Knowledge graph (KG) completion aims to fill the missing facts in a KG, where\na fact is represented as a triple in the form of $(subject, relation, object)$.\nCurrent KG completion models compel two-thirds of a triple provided (e.g.,\n$subject$ and $relation$) to predict the remaining one. In this paper, we\npropose a new model, which uses a KG-specific multi-layer recurrent neural\nnetwork (RNN) to model triples in a KG as sequences. It outperformed several\nstate-of-the-art KG completion models on the conventional entity prediction\ntask for many evaluation metrics, based on two benchmark datasets and a more\ndifficult dataset. Furthermore, our model is enabled by the sequential\ncharacteristic and thus capable of predicting the whole triples only given one\nentity. Our experiments demonstrated that our model achieved promising\nperformance on this new triple prediction task.","url_abs":"http://arxiv.org/abs/1810.12582v2","url_pdf":"http://arxiv.org/pdf/1810.12582v2.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":"dskg-a-deep-sequential-model-for-knowledge","repo_url":"https://github.com/nju-websoft/DSKG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}