Table 3.

Results (%) of the machine-learning and hybrid species taggers. Accuracy (%) of the machine-learning based species tagger and the hybrid species tagger as tested on the EPPI and TE devtest datasets. An 'Overall' score is the micro-average of a system's accuracy on both datasets.

	BL	EPPI Model	TE Model	Combined Model	EPPI Model+Rules	TE Model+Rules	Combined Model+Rules
EPPI devtest	60.56	73.03	58.67	72.28	74.24	59.67	73.77
TE devtest	30.22	67.15	69.82	67.20	67.53	70.14	67.47
Overall	48.88	70.77	62.96	70.33	71.66	63.70	71.34