Table 3 Mean (and standard deviation) of the original scores
From: How do machine-generated questions compare to human-generated questions?
|  | Knowledge base (n = 40) | Web (n = 20) | Professional (n = 20) |
|---|---|---|---|
Fluency | 4.05 (0.340) | 4.06 (0.479) | 4.00 (0.341) |
Ambiguity | 3.97 (0.331) | 4.05 (0.367) | 4.00 (0.322) |
Pedagogy | 2.72 (0.342) | 2.89 (0.254) | 2.94 (0.363) |
Depth | 2.59 (0.351) | 2.66 (0.360) | 2.93 (0.478) |
Relevance | 3.51 (0.460) | 3.92 (0.298) | 3.65 (0.409) |