Enhancing English to Amharic machine translation with prior knowledge integration: Leveraging syntactic structures of the source language

Abstract Machine translation has made significant progress in automating the conversion of human languages using computational methods. However, achieving human-level performance remains a challenge, particularly for languages such as Amharic. This paper aims to bridge this gap by integrating prior knowledge, particularly the syntactic structure of the source language, into Graph Neural Networks for English-to-Amharic machine translation. Our objective is to systematically evaluate the effectiveness of integrating syntactic information into Graph Neural Networks to improve translation quality. We conduct a thorough review of relevant literature and describe the preprocessing steps for both existing and newly collected parallel corpora used in training. Our approach involves preprocessing data and discussing the proposed Graph2Seq models. Experimental results demonstrate a notable 4.56% increase in bilingual evaluation understudy (BLEU) score compared to the baseline, indicating a significant improvement in translation quality. Moreover, our models exhibit a 1.98% enhancement in BLEU score over previous attempts, highlighting the value of integrating syntactic information into Graph Neural Networks. Through meticulous experimentation and analysis, we illustrate the efficacy of incorporating source language syntax into Graph Neural Networks for enhancing English-to-Amharic machine translation. This study contributes to the advancement of machine translation systems, particularly for low-resource languages, and lays the foundation for future research in integrating syntactic knowledge across diverse linguistic tasks and languages.