School of Foreign Languages, Nanchang Institute of Technology, Nanchang 330000, China.
J Environ Public Health. 2022 Aug 18;2022:5932044. doi: 10.1155/2022/5932044. eCollection 2022.
Large-scale corpus application has presented MT with new opportunities as well as challenges in recent years. This study investigates MT and post-translation editing capability using AI technology. The grammar rules of the target language are first examined. Then, a significant amount of data on semantic information entropy are projected, and the semantic Gaussian marginal rectangular window function is obtained. The semantic correlation factors of words are added to the text information entropy and information gain, and the nonlinear spectral properties of adaptive matching semantics are obtained. In this way, it corrects the significant flaw in the way semantic features are extracted using conventional techniques. In order to speed up MT and enhance translation quality, this study proposes automatic post-translation editing to filter those common MT errors that occur frequently and regularly. According to the experimental findings, word translation and segmentation accuracy can both reach 95.27 and 93.12 percent, respectively. In terms of language translation, this approach is accurate and trustworthy. I hope it will serve as a useful source for subsequent research.
近年来，大规模语料库的应用为机器翻译带来了新的机遇和挑战。本研究利用人工智能技术考察机器翻译和译后编辑能力。首先检验目标语言的语法规则，然后投射大量语义信息熵数据，并获得语义高斯边缘矩形窗口函数。将词的语义相关因素添加到文本信息熵和信息增益中，获得自适应匹配语义的非线性谱特性。这样就纠正了传统技术提取语义特征的显著缺陷。为了加快机器翻译速度，提高翻译质量，本研究提出了自动译后编辑，以过滤经常且规律出现的常见机器翻译错误。根据实验结果，词翻译和分词准确率分别可达 95.27%和 93.12%。在语言翻译方面，该方法准确可靠，希望能为后续研究提供有用的参考。
