Adaptation of language model of information retrieval for empty answers problem in databases

Information over the web is increasingly retrieved from relational databases in which the query language is based on exact matching, data fulfil completely the query or not. The results returned to the user contain only tuples that satisfy the conditions of the query. Thereby, the user can be confronted to the problem of empty answers in the case of too selective query. To overcome this problem, several approaches have been proposed in the literature in particularly those based on query conditions relaxation. Others works suggest the use of fuzzy sets theory to introduce a flexible queries. Another line of research proposes the adaptation of information retrieval (IR) approaches to get an approximate matching in databases. We discuss in this paper, an adaptation of language model of IR to deal with empty answers. The main idea behind our approach is that instead of returning an empty response to the user, a ranked list of tuples that have the most similar values to those specified in user´s query is returned.