Table 2.

Overall systems’ performance

	Internal test			Challenge test
Task	Precision	Recall	F1	Precision	Recall	F1
Concepts	0.8894	0.8962	0.8928	0.8586	0.8409	0.8497
Relations	0.9830	0.9754	0.9792	0.9455	0.9429	0.9442
End to end	0.8673	0.8711	0.8692	0.8382	0.7539	0.7938