Data Exploration on Large Amount of Relational Data through Keyword Queries

Abstract

The paper describes a new approach for querying relational databases through keyword search by exploting Information Retrieval (IR) techniques. When users do not know the structures and the content, keyword search becomes the only efficient and effective solution for allowing people exploring a relational database. The approach is based on a unified view of the database relations (performed through the full disjunction operator), where its composing tuples will be considered as documents to be indexed and searched by means of an IR search engine. Moreover, as it happens in relational databases, the system can merge the data stored in different documents for providing a complete answer to the user. In particular, two documents can be joined because either their tuples in the original database share some Primary Key or, always in the original database, some tuple is connected by a Primary / Foreign Key Relation. Our preliminary proposal, the description of the tabular data structure for storing and retrieving the possible connections among the documents and a metrics for scoring the results are introduced in the paper.