Table 4 Annotation categories for the human evaluation of the meaning of the generated text.
From: Generation and evaluation of artificial mental health records for Natural Language Processing
Category | Group | |
|---|---|---|
1 | Fully preserved | SAME |
2 | Preserved, details omitted | GOOD |
3 | Modified, does not contradict the diagnosis | GOOD |
4 | Modified, contradicts the diagnosis | BAD/IRR |
5 | Modified, irrelevant | BAD/IRR |
6 | No clinical sense | NO SENSE |
7 | Incomprehensible | NO SENSE |
