KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
share
We present KBLRN, a novel framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features. We discuss the advantages of each of the three feature types and the benefits of their combination. To the best of our knowledge, KBLRN is the first machine learning approach that learns representations of knowledge bases by integrating latent, relational, and numerical features. We show that instances of KBLRN outperform existing methods on a range of knowledge base completion tasks. For the experiments, we created novel data sets by enriching commonly used knowledge base completion benchmarks with numerical features. We also investigate in more detail the impact numerical features have on the link prediction performance.
READ FULL TEXT
