You have no items in your shopping cart.
ABSTRACT
This study focuses on the implementation of language model in diversifying the digital linguistic ecology. It seeks to create a language model using Igbo text datasets and neural network such as long short term memory (Lstm) and other machine learning frameworks to achieve this objective. The study explored the potential for a machine to recognize an African language, focusing on Igbo in this case. This work reviews prior research on language modeling, identifies best practices, and explores potential challenges in creating an Igbo language model. The basic concept of tools and frameworks used to build the language model were reviewed and discussed. The methodology employed in this study involves qualitative approaches. Under the qualitative data approach, the study utilizes secondary data collection, which involves the analysis of existing data sources and extraction of data from websites through a method called web scraping .The research delves further into developing the model, training the model on the sourced data, and using the evaluation metrics such as accuracy and precision to assess the model progress. The study builds and trains a language model capable of recognizing and processing Igbo language. This research reveals how machines learn language, what it entails to teach a machine a human language, and the tools and techniques used to achieve the research aim. Overall, this study attempts to create an Igbo language model focusing on development and implementation.
