Scribd
Upload
33 views1 page

Project Topic:: Desired Supervisor: Dr. LIENOU Jean-Pierre Co-Supervisor: Mr. SWI Innocent

The document proposes a project to build a deep neural network machine translation application that can translate English text to Medûmba, a Cameroonian vernacular language. The project will involve investigating datasets, pre-processing data by converting text to integers, creating and testing neural network models, and running the trained model on English text.

Uploaded by

ROLLIN RAMUS NDAYO FONTENG
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
33 views1 page

Project Topic:: Desired Supervisor: Dr. LIENOU Jean-Pierre Co-Supervisor: Mr. SWI Innocent

The document proposes a project to build a deep neural network machine translation application that can translate English text to Medûmba, a Cameroonian vernacular language. The project will involve investigating datasets, pre-processing data by converting text to integers, creating and testing neural network models, and running the trained model on English text.

Uploaded by

ROLLIN RAMUS NDAYO FONTENG
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

PROJECT TOPIC: Design and implementation of an application to translate national

languages to a Cameroonian vernacular using deep recurrent neural


networks: case study English to Medûmba

Project Summary:
Machine Translation is the translation of text or speech by a computer from one language to another
with no human intervention. It is a popular topic in research with different approaches being created,
like rule-based, statistical and example-based machine translation. Neural networks have made a great
advancement in machine translation. In this dissertation, I will discuss on the building of a deep neural
network that functions as a part of end-to-end translation channel. The complete application would
accept English text as input and return the text translated into Medûmba as output. The project will
be divided into four parts which are investigation of dataset, preprocessing, creation of models and
Running the model on English Text.

The first part on the investigation of dataset will be done to have a dataset that will be used to train
and test the application

The second, the pre-processing of the data will be a crucial step which will involve the conversion of
text to sequence of integers. This will be done since the text will not be taken as a direct input,

The third step will be the modeling part, which will consist the creation and testing of models

Finally the fourth part will be the running of the model.

Desired supervisor: Dr. LIENOU Jean-Pierre

Co-supervisor: Mr. SWI Innocent

Student information:
Name: Ndayo Fonteng Rollin Ramus
Registration Number: UBa19T0533
Level: 500
Option: Fundamental computer Science
Department: Computer Science
School: Higher Technical Teacher Training College Bambili.

You might also like