JIITA, vol. 2, no. 4, pp.167-175, Dec, 2018
Building a Language Model for the Cebuano Language
John Vincent N. Pakson 1), Robert R. Roxas 2,*)
1,2) Dept. of Computer Science, College of Science, University of the Philippines Cebu, Cebu City, Philippines
Abstract: This paper presents the result of building a language model for the Cebuano Language, which is greatly used in Central Visayas, Philippines. This language model is made possible using the Recurrent Neural Network (RNN) algorithm and a dataset of Cebuano articles translated from English articles by human translators and from online news articles in Cebuano. In this paper, we will also discuss the steps that we will be doing to determine the most suitable Language Model for Cebuano. The produced model expectedly generated a functional local language model that can be used in different aspects of today’s technologies such as spelling correction, word completion, automatic speech recognition, and machine translation.
Keyword: language model; Cebuano Language; recurrent neural network