Leveraging the schema in latent factor models for knowledge graph completion
Authors:
Open Access
- 4 April 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 327-332
Abstract
We focus on the problem of predicting missing links in large Knowledge Graphs (KGs), so to discover new facts. Over the last years, latent factor models for link prediction have been receiving an increasing interest: they achieve stateof-the-art accuracy in link prediction tasks, while scaling to very large KGs. However, KGs are often endowed with additional schema knowledge, describing entity classes, their sub-class relationships, and the domain and range of each predicate: the schema is actually not used by latent factor models proposed in the literature. In this work, we propose an unified method for leveraging additional schema knowledge in latent factor models, with the aim of learning more accurate link prediction models. Our experimental evaluations show the effectiveness of the proposed method on several KGsKeywords
This publication has 7 references indexed in Scilit:
- Large-scale factorization of type-constrained multi-relational data2014
- Constructing and mining web-scale knowledge graphs2014
- Knowledge vault2014
- A semantic matching energy function for learning with multi-relational dataMachine Learning, 2013
- DBpedia - A crystallization point for the Web of DataJournal of Web Semantics, 2009
- Foundations of Semantic Web Technologies2009
- Freebase2008