With the new advances of worldwide web, the need for the non-expert users to get access to the structured data has become more important. Ideally, users would like to write their question in natural language without worrying about the schema or the exact SQL queries that are needed to capture their information need. Moreover, when users express their information need in natural language, they tend to mean more than what they express. For example, when they ask about the “capital of Greece”, they may want to see more information in the answer than just “Athens”. On the other hand, there are different levels of disambiguation in keyword search process in general and in some cases it is not possible to find out about user’s intent without asking him, even while having a rich dataset in the back-end. Our proposed system introduces innovative approaches in order to provide user with an explanation about the result and to tackle the disambiguation in the query.
Introducing Feedback in Qanary: How Users can interact with QA systems. Dennis Diefenbach, Niousha Hormozi, Shanzay Amjad, Andreas Both, ESWC P&D 2017 PDF