Publication Date: 2024/10/10
Abstract: The goal of this study, "Automation of Answer Scripts Evaluation," is to create an end-to-end automated process that can quickly and fairly evaluate answer scripts and grade students. Optical Character Recognition (OCR), Artificial Intelligence (AI), Machine Learning (ML), Natural Language Processing (NLP) are brought together to build a workflow for automating this tedious, time taking, subjective activity. The paper discusses failures and successes of various models applied in our endeavour.
Keywords: OCR Model, Bert Model, NLP, GPT Model, Optimization, Cosine Similarity, Vectorization, Rubric Model, Evaluating Model, Datasets, Ensemble, Majority Voting, Gradient Descent.
DOI: https://doi.org/10.38124/ijisrt/IJISRT24OCT205
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT24OCT205.pdf
REFERENCES