Using Natural Language to Integrate, Evaluate, and Optimize Extracted Knowledge Bases

Web Information Extraction (WIE) systems extract billions of unique facts, but integrating the assertions into a coherent knowledge base and evaluating across different WIE tech-niques remains a challenge. We propose a framework that utilizes natural language to integrate and evaluate extracted knowledge bases (KBs). In the framework, KBs are inte-grated by exchanging probability distributions over natural language, and evaluated by how well the output distribu-tions predict held-out text. We describe the advantages of the approach, and detail remaining research challenges