Avaliando a similaridade semântica entre frases curtas através de uma abordagem híbrida

• Allan de Barcelos Silva Unisinos
• Sandro José Rigo Unisinos
• Isa Mara Alves Unisinos
• Jorge L. V. Barbosa Unisinos

Abstract

The task of evaluating textual semantic similarity is one of the challenges in the Natural Language Processing area. It is observed in the literature the experimentation with priority use of probabilistic resources, and linguistic aspects explored in an incipient way. This paper presents an experiment with a hybrid approach, in which both resources of distributed representation and also lexical and linguistic aspects are integrated for the evaluation of semantic similarity between short sentences in Brazilian Portuguese. The proposed technique was evaluated with a dataset known in the literature and obtained good results.