Answering Natural Language Questions by Sub graph Matching over Knowledge Graphs
The main aim of the project is to provide an effective question answering RDF system which is very easy to the users in a structural way utilizing semantic query graph model.
In this project, we propose a graph data-driven framework to answer natural language questions over RDF graphs. Different from existing work, we allow the ambiguity both of phrases and structure in the question understanding stage. We push down the disambiguation into the query evaluation stage. Based on the query results over RDF graphs, we can address the ambiguity issue efficiently. In other words, we combine the disambiguation and query evaluation in a uniform process. Consequently, the graph data-driven framework not only improves the precision but also speeds up the whole performance of RDF Q/A system.