A terminologia em Sistemas de Recuperação da Informação baseada na WORDNET.PT

Abstract

The aim of this paper is to propose a language-based information retrieval system to extract WordNet.Pt lexicalizations and relate them to the terms of the controlled vocabulary and search terms of users. The approach is qualitative, exploratory and applied to problem solving about ambiguity in information retrieval. As for the procedures used, this is a bibliographic search. The discussion is motivated by the problem of high recall, determined by the degree of similarity between user search expressions and corpus documents, without the precise determination of the semantics involved. The research nucleus is justified by the advantage of developing systems that combine natural language and controlled language oriented for an interactive search. Although partially, the research points to important results in solving lexical ambiguity through semantic relationships between natural and artificial language terms. On the one hand, this success guarantees the search space restriction and, consequently, the precision. On the other, the expansion of queries by suggesting equivalent terms of controlled vocabularies and the natural language and its variants.