Neural Machine Translation for Low-resource Languages: A Survey

By Surangika Ranathunga, E. Lee, Marjana Prifti Skenduli, Ravi Shekhar, Mehreen Alam, Rishemjit Kaur. ACM Computing Surveys, 2021

376 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/50c38435e38c227e9e8917f67aa6e0aca915b544

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models (2023, background): “In the domain of translation, by harnessing large language models and their capabilities, it is possible to achieve more accurate and ﬂuent translations across various languages [17], including low-resource ones [18, 19, 20, 21].”
Multilingual training for Software Engineering (2021, background): “Third,we find that quite often a model trained in one programming language achieves surprisingly good performance on a test set in a different language, sometimes even surpassing a model trained on the same language as the test set! Taken together, these findings suggest that pooling data across lan”
A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, neutral): “[9], Information Extraction [10]–[12], and Machine Translation [13], [14].”
Unveiling Security, Privacy, and Ethical Concerns of ChatGPT (2023, methodology): “Prior to the success of these methods, numerous effective algorithms and remarkable applications had been developed in NLP, including machine translation [3], [4], voice recognition [5], [6], and summary generation [7], [8].”
Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models (2026, unknown): “Zulu is a relatively low-resource language [41], and thus provides a good setting to explore the utility of synthetic data augmentation, here provided by a bespoke English-Zulu MT model built within the Sockeye Neural Machine Translation platform [42].”