Automated Essay Grading

  • Vinay Sanga, Shreyansh Patil, Abhishek Jagtap, Prashant Raut, Geeta S Navale


In the task of essay grading a grade is assigned to an essay in the most human-like manner possible. Authors tackle this problem by building statistical models which try and predict how a human would evaluate an essay. In this paper, we propose to use Long Short Term Memory (LSTM) neural networks to create an essay grader to undertake this daunting task. The grader will give an essay a grade which would be expected from a human grader. The user will be able to see his score instantaneously which is an improvement as compared to human graders. There are some very challenging tasks such as recognizing the context of the essay. Also, the vocabulary and various versions of English will have to be considered while evaluating the essay. The grader will be able to grade an essay without any bias and high accuracy.