Amharic-Arabic Neural Machine Translation

TL;DR

This paper develops and compares LSTM and GRU neural machine translation models for Amharic-Arabic, demonstrating that LSTM-based models outperform GRU and Google Translate on a Quranic corpus.

Contribution

It introduces the first Amharic-Arabic NMT models using LSTM and GRU architectures with attention, addressing data scarcity and providing a comparative analysis.

Findings

LSTM-based NMT outperforms GRU-based NMT.

LSTM NMT achieves BLEU score of 12%.

Google Translate scores 6% BLEU.

Abstract

Many automatic translation works have been addressed between major European language pairs, by taking advantage of large scale parallel corpora, but very few research works are conducted on the Amharic-Arabic language pair due to its parallel data scarcity. Two Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) based Neural Machine Translation (NMT) models are developed using Attention-based Encoder-Decoder architecture which is adapted from the open-source OpenNMT system. In order to perform the experiment, a small parallel Quranic text corpus is constructed by modifying the existing monolingual Arabic text and its equivalent translation of Amharic language text corpora available on Tanzile. LSTM and GRU based NMT models and Google Translation system are compared and found that LSTM based OpenNMT outperforms GRU based OpenNMT and Google Translation system, with a BLEU score of 12%, 11%, and 6% respectively.