Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits

This paper introduces 'Marking', a novel automated grading task that goes beyond binary scoring by highlighting correct/incorrect/irrelevant segments in student responses and identifying omissions from gold answers. The authors create the BioMarking dataset (curated by biology experts) and train transformer models (BERT, RoBERTa) to perform fine-grained assessment of student responses.

In this paper, we introduce"Marking", a novel grading task that enhances automated grading systems by performing an in-depth analysis of student responses and providing students with visual highlights. Unlike traditional systems that provide binary scores,"marking"identifies and categorizes segments of the student response as correct, incorrect, or irrelevant and detects omissions from gold answers. We introduce a new dataset meticulously curated by Subject Matter Experts specifically for this t

Study Type

Source

Framework Categories

Tool Types

Tags