The Automatic Scoring Method of English Translation for College Students Considering Latent Semantics

The ultimate goal of this study is to design and develop a Latent Semantic Analysis-Document Relevance Score-Entropy-Based Translation Fluency (LD-ENTF) scoring method that takes into account both latent semantics and chapter structure, to solve the scoring problem of subjective translation questions. First, the latent semantics are transformed into vectors and subjected to singular value decomposition to capture the deep semantics of the translated text. Next, we use the TF-IDF method to measure the importance of words to ensure accurate evaluation of keywords. Subsequently, in terms of the structure of the translated chapters, the Metric for Evaluation of Translation with Explicit Ordering (METEOR) method is used to transform the sentences into chapter representation structures and align the corresponding words. Finally, the entropy of the translation is calculated using the ENTF method to obtain the final score. In the comparison experiments with Entropy-Based Translation Fluency, Translation Edit Rate, Bilingual Evaluation Understudy and Metric for Evaluation of Translation with Explicit Ordering methods, the LD-ENTF scoring method showed excellent performance. It achieved the highest accuracy of 0.993 and the lowest of 0.95. Its average accuracy was 0.97 and the root-mean-square error was 1.023. The LD-ENTF scoring method can significantly improve the accuracy and efficiency of translation evaluation by comprehensively considering Latent Semantic Analysis and Chapter Structure Analysis, promote high-quality dissemination and exchange of academic research results worldwide and assist in knowledge management.