Figure 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
In recent years, Chinese has become one of the most popular languages globally. The demand for automatic Chinese sentence correction has gradually increased. This research can be adopted to Chinese language learning to reduce the cost of learning and feedback time, and help writers check for wrong words. The traditional way to do Chinese sentence c...
Context in source publication
Citations
... In Asia, Japan has been one of the hottest countries for Chinese language teaching, almost every university has a Chinese language course, and Chinese has become one of the optional foreign languages in the college entrance examination for secondary school students [2]. In South Korea, China's closest neighbor, more than one million people are learning Chinese, two-thirds of the more than 300 universities have Chinese language courses, and language institutes for learning Chinese are located in all major cities [3]. ...
The systematic training of metacognitive strategies in teaching Chinese as a foreign language, cultivating learners’ autonomous learning ability, and improving the effectiveness of teaching Chinese as a foreign language is of great significance for realizing the overall goal of teaching Chinese as a foreign language. Therefore, this paper designs a model based on CDIO to guide the teaching of data structures and algorithms, which emphasizes students’ hands-on ability, advocates learning in use, students’ autonomous learning, and teamwork. Taking massive online open courses(MOOC ) and small private online courses ( SPOC) learning data as a sample, hidden Markov algorithm and data mining technology are used to establish a student learning behavior evaluation model to evaluate students’ learning behavior in real-time. Meanwhile, teachers adjust the teaching content according to the evaluation results and enhance students’ learning performance and improve teaching quality.
... Thus, Chen et al. proposed the acceleration of sentence correction tasks in Chinese, using a BERT-RNN model trained by applying the TF technique as an additional measure to accelerate the training process. After experimentation with various recurrent models functioning as decoder, the BERT-GRU combination outperformed the best BLEU metric, and improved the inference time of the base transformer model by 1131% [23]. ...
This paper focuses on
visual attention
, a state-of-the-art approach for image captioning tasks within the computer vision research area. We study the impact that different hyperparemeter configurations on an encoder-decoder visual attention architecture in terms of efficiency. Results show that the correct selection of both the cost function and the gradient-based optimizer can significantly impact the captioning results. Our system considers the cross-entropy, Kullback-Leibler divergence, mean squared error, and negative log-likelihood loss functions; the adaptive momentum (Adam), AdamW, RMSprop, stochastic gradient descent, and Adadelta optimizers. Experimentation shows that a combination of cross-entropy with Adam is the best alternative returning a Top-5 accuracy value of 73.092 and a BLEU-4 value of 20.10. Furthermore, a comparative analysis of alternative convolutional architectures demonstrated their performance as an encoder. Our results show that ResNext-101 stands out with a Top-5 accuracy of 73.128 and a BLEU-4 of 19.80; positioning itself as the best option when looking for the optimum captioning quality. However, MobileNetV3 proved to be a much more compact alternative with 2,971,952 parameters and 0.23 Giga fixed-point Multiply-Accumulate operations per Second (GMACS). Consequently, MobileNetV3 offers a competitive output quality at the cost of lower computational performance, supported by values of 19.50 and 72.928 for the BLEU-4 and Top-5 accuracy, respectively. Finally, when testing vision transformer (ViT), and data-efficient image transformer (DeiT) models to replace the convolutional component of the architecture, DeiT achieved an improvement over ViT, obtaining a value of 34.44 in the BLEU-4 metric.
