Neural Machine Translation for Low-Resource Languages: A Survey

• DOI: 10.48550/arxiv.2106.15115
• Publication Date: 2023-02-09
• Authors: Surangika Ranathunga; En-Shiun Annie Lee; Marjana Prifti Sk...; Ravi Shekhar; Mehreen Alam; Rishemjit Kaur
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; I.2.7; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computation and Language (cs.CL); 01 natural sciences; 0105 earth and related environmental sciences

Neural Machine Translation (NMT) has seen tremendous growth in the last ten years since the early 2000s and has already entered a mature phase. While considered the most widely used solution for Machine Translation, its performance on low-resource language pairs remains sub-optimal compared to the high-resource counterparts due to the unavailability of large parallel corpora. Therefore, the implementation of NMT techniques for low-resource language pairs has been receiving the spotlight recently, thus leading to substantial research on this topic. This article presents a detailed survey of research advancements in low-resource language NMT (LRL-NMT) and quantitative analysis to identify the most popular techniques. We provide guidelines to select the possible NMT technique for a given LRL data setting based on our findings. We also present a holistic view of the LRL-NMT research landscape and provide recommendations to enhance the research efforts further.