QUASL: A Framework for Question Answering and its Application to Business Intelligence

Nicolas Kuchmann-Beauger (1, 2) , Falk Brauer (3) , Marie-Aude Aufaure (1)

1 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
2 SAP Research [Dresden]
3 SAP Asia Pte Ltd

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 we 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. It bases on popular standards like RDF and SparQL and is therefore very easy to adapt to other domains or use- cases. We will describe the application of this framework at hand of a BI question answering use-case, which also includes the personalization of generated queries, demonstrating the real- world applicability of our approach. In our experiments, we demonstrate that with our approach one can easily achieve a similar answering quality as one of the most popular Q&A systems on the Web.

Domaines: Informatique et langage [cs.CL]

Nicolas Kuchmann-Beauger, Falk Brauer, Marie-Aude Aufaure. QUASL: A Framework for Question Answering and its Application to Business Intelligence. Proceedings of the 7th International Conference on Research Challenges in Information Science, 2013, pp.143. ⟨hal-00835567⟩