Neural Machine Translation for Low-resource Languages: A Survey

• Published in: ACM computing surveys Vol. 55; no. 11; pp. 1 - 37
• Main Authors: Ranathunga, Surangika, Lee, En-Shiun Annie, Prifti Skenduli, Marjana, Shekhar, Ravi, Alam, Mehreen, Kaur, Rishemjit
• Format: Journal Article
• Language: English
• Published: New York, NY ACM 30.11.2023; Association for Computing Machinery
• Subjects: Computer science; Computing methodologies; Language resources; Machine learning; Machine translation; Natural language processing; Neural networks; pivoting; semi-supervised NMT; transfer learning; low-resource languages; data augmentation; Neural machine translation; unsupervised NMT; multilingual NMT; zero-shot translation
• ISSN: 0360-0300; 1557-7341
• DOI: 10.1145/3567592

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.