From: Natural language processing for automatic evaluation of free-text answers — a feasibility study based on the European Diploma in Radiology examination
Dataset
Marking (0–3 and 0–4, respectively)
Total
0
1
2
3
4
Case 980 “unstructured question 1”
13
37
21
25
NA
96
Case 959 “unstructured question 2”
14
112
90
80
31
327
Case 457 “more structured question”
38
30
6
111