Question answering system using multiple information source and open type answer merge

Abstract

This paper presents a multi-strategy and multi-source question answering (QA) system that can use multiple strategies to both answer natural language (NL) questions and respond to keywords. We use multiple information sources including curated knowledge base, raw text, auto-generated triples, and NL processing results. We develop open semantic answer type detector for answer merging and improve previous developed single QA modules such as knowledge base based QA, information retrieval based QA.