Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach
arXiv:1806.09504
Abstract
Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt "pedagogical approaches" (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.
arXiv commentpresented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
References in corpus (9)
- Efficient Estimation of Word Representations in Vector Space
- A Review of Relational Machine Learning for Knowledge Graphs
- Complex Embeddings for Simple Link Prediction
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
- What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
- Analogical Inference for Multi-Relational Embeddings
- Neighborhood Mixture Model for Knowledge Base Completion
- An Interpretable Knowledge Transfer Model for Knowledge Base Completion
- Inducing Interpretability in Knowledge Graph Embeddings