CLASSIFICATION OF BAOULE SENTENCES ACCORDING TO FREQUENCY AND SEGMENTATION OF TERMS VIA CONVOLUTIONAL NEURAL NETWORKS

In the Baoule language, several sentences express the same fact. Classification of sentences is a task of Natural Language Processing (NLP). Deep learning has turned out to be a kind of method that has a significant effect in this area. In this paper, we propose a convolutional neural network (CNN) based system for sentence classification. We introduce into this system a word representation model to capture semantic characteristics by encoding the frequency of terms and segmenting the sentence into clauses. The experimental results show that our system produces satisfactory results.