Table 10 Ratings for a specific question that was generated identically by a human expert and the system
From: Evaluation of a question generation approach using semantic web for supporting argumentation
Understandability | Relevance | Usefulness | ||||||
|---|---|---|---|---|---|---|---|---|
Rater 1 | Rater 2 | Mean | Rater 1 | Rater 2 | Mean | Rater 1 | Rater 2 | Mean |
3 | 3 | 3 | 3 | 1 | 2 | 2 | 1 | 1.5 |