Quality Assessment of Machine Translation (on the material of Russian-Chinese translation of scientific aerospace texts)
Abstract
With the rapid development of artificial intelligence, machine translation has come to be regarded as an effective tool for assisting or even replacing human translation, and its utilization has become increasingly widespread. This study employs a Russian aerospace monograph as the test corpus, introduces the BLEU metric for evaluation, and assesses the translations produced by four prominent machine translation engines: Google Translate, DeepL Translate, Baidu Translate, and ChatGPT Translate. It generalizes and summarizes the prevalent issues encountered at the vocabulary, grammar, and chapter levels when machine software translates Russian scientific texts. Furthermore, the current study proposes improvement suggestions aimed at enhancing the quality of these translations.
Fields of Study & Subjects
Translation Studies and Practices
Natural Language Processing Techniques
Text Readability and Simplification
Publication details
- Journal / source
- Vestnik NSU Series Linguistics and Intercultural Communication
- Volume
- 23
- Issue
- 3
- Pages
- 136–150
- Publication date
- 11 February 2026
- Language
- EN