Ecole Centrale Paris
Question Answering (Q&A) from structured data is a technique that may revolutionize enterprise search. A very promising use-case for such technology is Business Intelligence (BI). In order to make BI more accessible to end-users, some efforts have been made in the field of search for existing reports. However, the problem of converting an end-user's natural language input to a valid structured query in an ad-hoc fashion hasn't been sufficiently solved yet. In this paper, the authors present a framework for Q&A systems that operate on structured data. The main innovation is that the framework allows defining a mapping between recognized semantics of a user's questions to a structured query model that can be executed on arbitrary data sources.