Dialog Navigator: A Question Answering System based on Large Text Knowledge Base.

Abstract

This paper describes a dialog based QA system, Dialog Navigator, which can answer questions based on large text knowledge base. In real world QA systems, vagueness of questions is a big problem. Our system can navigate users to the desired answers using the following meth-ods: asking users back with dialog cards, and description extraction of each retrieved text. Another feature of the system is that it re-trieves relevant texts precisely, using question types, synonymous expression dictionary, and modifier-head relations in Japanese sentences.