{"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/augmenting-compositional-models-for-knowledge","title":"Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations","arxiv_id":"1811.01062","date":"2018-11-02","proceeding":null,"authors":["Matthias Lalisse","Paul Smolensky"],"abstract":"Neural models of Knowledge Base data have typically employed compositional representations of graph objects: entity and relation embeddings are systematically combined to evaluate the truth of a candidate Knowedge Base entry. Using a model inspired by Harmonic Grammar, we propose to tokenize triplet embeddings by subjecting them to a process of optimization with respect to learned well-formedness conditions on Knowledge Base triplets. The resulting model, known as Gradient Graphs, leads to sizable improvements when implemented as a companion to compositional models. Also, we show that the \"supracompositional\" triplet token embeddings it produces have interpretable properties that prove helpful in performing inference on the resulting triplet representations.","url_abs":"https://arxiv.org/abs/1811.01062v2","url_pdf":"https://arxiv.org/pdf/1811.01062v2.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":[],"tasks":[{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-graphs-on-fb15k","task":"Knowledge Graphs","dataset":"FB15k","model":"HHolE","rank_in_archive_order":1,"of":2,"metrics":{"MRR":".796"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k-1","task":"Link Prediction","dataset":"FB15k","model":"HHolE","rank_in_archive_order":4,"of":10,"metrics":{"Hits@1":"0.727","Hits@10":"0.901","Hits@3":"0.848","MR":"21","MRR":"0.796"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k","task":"Link Prediction","dataset":"FB15k","model":"HHolE","rank_in_archive_order":8,"of":23,"metrics":{"Hits@1":".727","Hits@10":".901","Hits@3":".848","MR":"21","MRR":".796"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"HHolE","rank_in_archive_order":20,"of":37,"metrics":{"Hits@1":".931","Hits@10":".951","Hits@3":".945","MR":"183","MRR":".939"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}