Bi-directional English-Awngi Machine Translation Using Deep learning

Agerie, Belete

dc.contributor.author	Agerie, Belete
dc.date.accessioned	2022-11-16T12:18:16Z
dc.date.available	2022-11-16T12:18:16Z
dc.date.issued	2022-08
dc.identifier.uri	http://ir.bdu.edu.et/handle/123456789/14432
dc.description.abstract	Deep learning is the current approach in neural machine translation, which requires huge amount of parallel corpus to produce high-quality translation result. The purpose of the study is to develop a bidirectional translation of the English Awngi language pairs using deep learning. Languages need to be translated into other languages to transfer knowledge between language speakers. The use of computer software used to translate one natural language into another is called machine translation. We have conducted the experiment based on LSTM, CNN and Transformer models. Among those models transformer model achieves a BLEU score of 25.78 & 24.94 from English-Awngi and 23.56 & 22.34 from Awngi-English from simple and complex sentences respectively. Keywords— Neural Machine Translation, Deep learning, English-Awngi Machine Translation, LSTM, CNN, Transformer	en_US
dc.language.iso	en_US	en_US
dc.subject	FACULTY OF COMPUTING	en_US
dc.title	Bi-directional English-Awngi Machine Translation Using Deep learning	en_US
dc.type	Thesis	en_US