A

AutoCorrect

Rapid Automated Correction of Desriptive Answer Scripts using Knowledge Graphs and Word Embeddings

A

AutoCorrect

Rapid Automated Correction of Desriptive Answer Scripts using Knowledge Graphs and Word Embeddings

The problem AutoCorrect solves

Correction of papers is a strenuous and physically tiring task. It requires constant concentration and a clear conscience and fair hand to mark answers and award a candidate their deserved marks. During Examinations, over thousands of papers are sometimes corrected, with some teachers putting in the effort to correct almost a hundred papers every day. This ardent effort sometimes leads to mistakes creeping in, or a non-standardised method of evaluation. We need to find a way to not only reduce the pressure on teachers during exam sessions but also speed up the process of correction.

Challenges we ran into

The application has a significant boot-up time of 30 seconds since it starts a server (Stanford coreNLP). There were also platform dependency based issues since some libraries used were harder to install on Windows.

Discussion