Dong Xi, Limin Li

Limin Li

November 28, 2025

Low-resource language, Machine translation, Mongolian-Chinese machine translation, Bibliometric analysis, Knowledge graph, Low-resource language pairs.

Machine translation for low-resource languages is a key focus in translation studies. In this paper, CiteSpace was employed to perform a bibliometric analysis of 109 core articles on Mongolian-Chinese machine translation retrieved from CNKI between 2002 and 2024. This analysis systematically maps the latest progress and research trends in this field. The results show that research on Mongolian-Chinese machine translation in China has evolved through three distinct phases: initial exploration, fluctuating growth, and stable development. Although the research on Mongolian-Chinese machine translation has achieved remarkable results, its translation performance still needs to be improved compared with high-resource language models. Current research in this field focuses on Neural Machine Translation. Researchers have primarily focused on methods such as adversarial learning, dual learning, transfer learning, data augmentation, and pre-training to continuously train, iterate, and optimize translation systems, with the goal of enhancing translation performance.

© 2025, the Authors. Published by ISCCAC

This is an open access article distributed under the CC BY-NC license