A content-aware hybrid architecture for answering questions from open-domain texts

The current work blends the different paradigms of Question Answering systems and presents a content-aware hybrid architecture for an open-domain factoid questions. It combines a knowledge-based, information extraction-based and a web-based approach in a pipelined architecture to construct an answer to a question keeping the context and discourse of the question in view. The proposed semantic-aware hybrid architecture was compared with other QA systems designed over standard benchmark data. The work has shown enough potential in terms of accuracy and time domain complexity and can be used effectively as a semantic understanding-based QA system.