Along with the pace of educational reform in colleges and universities, a variety of new types of teaching and research approaches stand out in each subject taught in colleges and universities. For example, in college English lectures, given the practice of individualized tiered teaching, the development of relevant teaching models for students at different levels has become a new type of teaching and research developed year by year. Based on the English classroom program, teachers should make cognizance of the tiered teaching model when teaching. This paper discusses the tiered teaching method of English teaching and carries out teaching from strategies such as paying attention to students’ tiered teaching, doing well in lecture tiered teaching, developing homework tiered teaching, and paying attention to evaluation tiered teaching. In addition, the assessment system of college English courses lags behind the development of college English teaching reform and cannot play a guiding role in teaching. In response to the above-mentioned views and problems, this paper proposes a convolutional neural network-based algorithm that provides different learning styles for different students in the stratified teaching method of college English, making capable students understand what they learn in class, improving the teaching quality of high school English courses, and, at the same time, establishing a standardized and scientific course with high reliability and validity that meets the actual situation of applied technical college students. At the same time, a standardized and scientific course assessment system with high reliability and validity has been established to meet the actual needs of applied technical college students.

The current automatic recognition method of machine English translation errors has poor semantic analysis ability, resulting in low accuracy of recognition results. Therefore, this paper designs an automatic recognition method for machine English translation errors based on multifeature fusion. Manually classify and summarize the real error sentence pairs, falsify a large amount of data by means of data enhancement, enhance the effect and robustness of the machine translation error detection model, and add the source text to translation length ratio information and the translation language model PPL into the model input. The score feature information can further improve the classification accuracy of the error detection model. Based on this error detection scheme, the detection results can be used for subsequent error correction and can also be used for error prompts to provide translation user experience; it can also be used for evaluation indicators of machine translation effects. The experimental results show that the word posterior probability features calculated by different methods have a significant impact on the classification error rate, and adding source word features based on the combination of word posterior probability and linguistic features can significantly reduce the classification error rate, to improve the translation error detection ability.