ViBidirectionMT - Eval: Machine translation for Vietnamese-Chinese and Vietnamese-Lao language pair

Tran Hong Viet, Nguyen Minh Quy, Nguyen Van Vinh
Author affiliations

Authors

  • Tran Hong Viet University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam, 144 Xuan Thuy Street, Ha Noi, Viet Nam
  • Nguyen Minh Quy University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam, 144 Xuan Thuy Street, Ha Noi, Viet Nam
  • Nguyen Van Vinh University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam, 144 Xuan Thuy Street, Ha Noi, Viet Nam

DOI:

https://doi.org/10.15625/1813-9663/21055

Keywords:

Machine translation, neural machine translation, low-resource, translation error analysis.

Abstract

This paper presents the results of the VLSP 2022-2023 Machine Translation Shared Tasks, focusing on Vietnamese-Chinese and Vietnamese-Lao machine translation. The tasks were organized as part of the 9th and 10th annual workshops on Vietnamese Language and Speech Processing (VLSP 2022, VLSP 2023). The objective of the shared task was to build machine translation systems, specifically targeting Vietnamese-Chinese and Vietnamese-Lao translation (corresponding to 4 translation directions). The submissions were evaluated on 1,000 test pairs from both news and general domains, using established metrics such as BLEU and SacreBLEU. In addition to these automated evaluations, the system outputs were also assessed through human judgment by experts in the Chinese and Lao languages. These human assessments played a crucial role in ranking the performance of the machine translation models, ensuring a more comprehensive evaluation.

References

Downloads

Published

23-09-2025

How to Cite

[1]T. H. Viet, N. M. Quy, and N. V. Vinh, “ViBidirectionMT - Eval: Machine translation for Vietnamese-Chinese and Vietnamese-Lao language pair”, J. Comput. Sci. Cybern., vol. 41, no. 3, p. 285–304, Sep. 2025.

Issue

Section

Articles

Similar Articles

<< < 6 7 8 9 10 11 12 13 14 15 > >> 

You may also start an advanced similarity search for this article.