@inproceedings{e656c3c34127415b95195787b9947064,
title = "The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation",
abstract = "Machine translation (MT) is one of the prominent tasks in natural language processing whose objective is to translate texts automatically from one natural language to another. Nowadays, using deep neural networks for MT task has received a great deal of attention. These networks require lots of data to learn abstract representations of the input and store it in continuous vectors. This paper presents the first relatively large-scale Amharic-English parallel sentence dataset. Using these compiled data, we build bi-directional Amharic-English translation models by fine-tuning the existing Facebook M2M100 pre-trained model achieving a BLEU score of 37.79 in Amharic-English translation and 32.74 in English-Amharic translation. Additionally, we explore the effects of Amharic homophone normalization on the machine translation task. The results show that normalization of Amharic homophone characters increases the performance of Amharic-English machine translation in both directions.",
keywords = "Amharic-English MT, Neural machine translation, homophone normalization, low-resourced language, pre-trained models",
author = "Belay, {Tadesse Destaw} and Tonja, {Atnafu Lambebo} and Olga Kolesnikova and Yimam, {Seid Muhie} and Ayele, {Abinew Ali} and Haile, {Silesh Bogale} and Grigori Sidorov and Alexander Gelbukh",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Information and Communication Technology for Development for Africa, ICT4DA 2022 ; Conference date: 28-11-2022 Through 30-11-2022",
year = "2022",
doi = "10.1109/ICT4DA56482.2022.9971385",
language = "Ingl{\'e}s",
series = "2022 International Conference on Information and Communication Technology for Development for Africa, ICT4DA 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "84--89",
editor = "Esubalew Alemneh and Ethiopia Nigussie and Fisseha Mekuria",
booktitle = "2022 International Conference on Information and Communication Technology for Development for Africa, ICT4DA 2022",
address = "Estados Unidos",
}