Narrow Results

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.

Automatic scoring of students’ physical experimental operations is a very practical application which has not been researched deeply. The common method for automatic scoring of students’ experimental operations is to infer the behavior of experimental operations through the state of experimental instruments. Video object detection is the basic task of detecting the state of experimental instruments, and the problem of missed detection or false detection in video multi-object detection is one of the main reasons leading to the error of automatic scoring results. However, existing methods of video object detection mainly improve the accuracy of the model in public datasets, which has the disadvantage of not correcting false detection while improving accuracy. Therefore, an efficient video object detection method composed of YOLOv5 and a logical reasoning post-processing method was proposed to fill this gap. We compared our method with other state-of-the-art methods on three independent datasets of physical experimental instruments. We established a pipeline for automatic scoring of students’ experimental operations, designed flow charts and state score tables of three physics experiments, and compared the automatic scoring results with the average scores of six experimental teachers. The results show that our method is more robust and efficient in this application scenario. We hope this report can promote the application of logical reasoning methods in video object detection.