Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach
This work addresses the interpretability challenge in knowledge base completion, which is crucial for applications in natural language processing and semantic web search, though it represents an incremental adaptation of existing methods.
The paper tackles the problem of interpreting embedding models for knowledge base completion by adapting pedagogical approaches from neural networks to extract weighted Horn rules, demonstrating their effectiveness and limitations through experimental evaluation.
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.