Automatic Marking based on Deep Learning

In order to solve the problem of a lot of time and energy being wasted when the marking teacher corrects the test papers, this paper proposes an automated test paper correction system based on deep learning. The system is roughly divided into three modules: text extraction from test papers, text encoding and text matching. Using the method of combining DB and CRNN to extract text from the test paper, it has a high accuracy of text recognition; and respectively uses the BERT pre-training model and cosine similarity as the method of text encoding and text matching. The experimental results prove that the automated test paper The average result of the correction system and the scoring teacher's score is only 0.5, which achieves an excellent evaluation effect.