Generating OLAP Queries from Natural Language Specification

Automatic translation of natural language (NL) questions to Structured Query Language (SQL) queries is a challenging task. It is a common knowledge that writing Online Analytical Processing (OLAP) queries for data warehouses is difficult, particularly, for the novice users. In this paper, we present a natural language processing based approach to automatically generate OLAP queries those can be used to communicate with the a data warehouse. In the presented approach, user provides queries in English and our approach process English queries and generate OLAP queries. In our approach, we incorporate OMG's recent standard Semantic of Business Vocabulary and Business Rules (SBVR) to simplify the translation process of English to OLAP. SBVR is used in detailed semantic analysis of English queries. The presented approach is also implemented in Java as a prototype tool. To test the performance of the tool, an experimental study is also conducted. Results of the experimental study imply that our approach is capable in communicating with a data warehouse.