Corpus-Based Machine Translation for English to Low-Resource Language Using OpenNMT

One of the challenges in computational linguistics is the scope of Machine Translation (MT) for languages with few resources, specifically English to low-resource languages. Lack of parallel data in the majority of South-Asian languages prevents Machine Translation training. Computational linguistics plays a pivotal role in the storage of meaning and representation for specific object languages, and translation is a central component of language technology. This abstract explores the evolution of translation techniques, transitioning from direct word-to-word approaches to cutting-edge methods like Statistical Machine Translation (SMT) and Neural Machine Translation (NMT), enabled by neural networks and deep learning. However, despite these advancements, many South-Asian languages still face challenges due to the scarcity of parallel data for Machine Translation. This paper focuses on corpus-based machine translation and highlights various machine translation approaches. To address the issue of partial translations, an enhanced attention method is proposed, enhancing the decoder's ability to grasp contextual information. This abstract offers a glimpse into the significance of machine translation in the realm of computational linguistics and emphasizes the ongoing quest for more effective and accurate language translation solutions.