Table 10.

Average scores for each system and each batch of phase B of Task 1b for the “ideal” answers

System	Batch 1	Batch 2	Batch 3
Wishart-S1	3.95	4.23	-
Wishart-S2	3.95	-	-
Wishart-S3	3.95	-	-
Baseline1	2.86	3.02	3.19
Baseline2	2.73	2.87	3.17
main system	3.35	3.39	3.13
system 2	-	3.34	3.07
system 3	-	3.34	2.98
system 4	-	3.34	-

The final score is calculated as the average of the individual scores of the systems for the different evaluation criteria. A hyphenation symbol (-) is used whenever the system did not participate in the corresponding batch. The scores are given by experts who read and evaluated the “ideal” answers, and they range from 1 to 5, with 5 being the best score.