Open AccessCLASSIFICATION OF BAOULE SENTENCES ACCORDING TO FREQUENCY AND SEGMENTATION OF TERMS VIA CONVOLUTIONAL NEURAL NETWORKS
Author(s) -
Hyacinthe Kouassi Konan,
Francis Adles Kouassi,
Guy L. Diety,
Olivier Asseu
Publication year - 2022
Publication title -
international journal of advanced research
Language(s) - English
Resource type - Journals
ISSN - 2320-5407
DOI - 10.21474/ijar01/14012
Subject(s) - sentence , computer science , natural language processing , artificial intelligence , convolutional neural network , segmentation , representation (politics) , task (project management) , politics , political science , law , management , economics
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.