Neural Machine translation is a challenging task due to the inherent complex nature and the fluidity that natural languages bring. Nonetheless, in recent years, it has achieved state-of-the-art performance in several language pairs. Although, a lot of traction can be seen in the areas of multilingual neural machine translation (MNMT) in the recent years, there are no comprehensive survey done to identify what approaches work well. The goal of this project is to investigate the realm of low resource languages and build a Neural Machine Translation model to achieve state-of-the-art results. The project looks to build upon the \texttt{mBART.CC25} \cite{liu2020multilingual} language model and explore strategies to augment it with various NLP and Deep Learning techniques like back translation and transfer learning. This implementation tries to unpack the architecture of the NMT application and determine the different components which offers us opportunities to amend the said application within the purview of the low resource languages problem space.

翻译：神经机器翻译因自然语言的固有复杂性及流变性而充满挑战。然而，近年来，其在多个语言对中已取得最先进性能。尽管多语言神经机器翻译领域近年来备受关注，但尚无系统性综述研究以明确何种方法行之有效。本项目旨在探索低资源语言领域，构建达到最先进水平的神经机器翻译模型。项目计划基于\texttt{mBART.CC25} \cite{liu2020multilingual}语言模型，并探索结合回译、迁移学习等自然语言处理与深度学习技术对其进行增强的策略。本实现致力于解析神经机器翻译应用的架构，识别其不同组件，从而为我们在低资源语言问题空间内修正上述应用提供机遇。