Query-Driven Knowledge Graph Construction using Question Answering and Multimodal Fusion

Over recent years, large knowledge bases have been constructed to store massive knowledge graphs. However, these knowledge graphs are highly incomplete. To solve this problem, we propose a web-based question answering system with multimodal fusion of unstructured and structured information, to fill in missing information for knowledge bases. To utilize unstructured information from the Web for knowledge graph construction, we design multimodal features and question templates to extract missing facts, which can achieve good quality with very few questions. The question answering system also employs structured information from knowledge bases, such as entity types and entity-to-entity relatedness, to help improve extraction quality. To improve system efficiency, we utilize a few query-driven techniques for web-based question answering to reduce the runtime and provide fast responses to user queries. Extensive experiments have been conducted to demonstrate the effectiveness and efficiency of our system.