Text prediction recurrent neural networks using long short-term memory-dropout

Iparraguirre-Villanueva O.; Guevara-Ponce V.; Ruiz-Alvarado D.; Beltozar-Clemente S.; Sierra-Liñan F.; Zapata-Paulini J.; Cabanillas-Carbonell M. · Indonesian Journal of Electrical Engineering and Computer Science (2023) · DOI: 10.11591/ijeecs.v29.i3.pp1758-1768

Resumen

Unit short-term memory (LSTM) is a type of recurrent neural network (RNN) whose sequence-based models are being used in text generation and/or prediction tasks, question answering, and classification systems due to their ability to learn long-term dependencies. The present research integrates the LSTM network and dropout technique to generate a text from a corpus as input, a model is developed to find the best way to extract the words from the context. For training the model, the poem "La Ciudad y los perros" which is composed of 128,600 words is used as input data. The poem was divided into two data sets, 38.88% for training and the remaining 61.12% for testing the model. The proposed model was tested in two variants: word importance and context. The results were evaluated in terms of the semantic proximity of the generated text to the given context.

Instituciones: Universidad Científica del Sur; Universidad Ricardo Palma; Universidad Continental; Universidad Autónoma del Perú; Universidad Privada Norbert Wiener; Universidad Privada del Norte