On Multilabel Classification Methods of Incompletely Labeled Biomedical Text Data

Table 8

Microaveraged results for SVM, trained on “incompletely labeled” Yeast dataset (with different fraction of deleted labels 𝑝).

𝑝 parameter	Precision	Recall	𝐹1
0	0.7176	0.5707	0.6358
0.1	0.7337	0.5233	0.6109
0.2	0.7354	0.4056	0.5229
0.3	0.6260	0.2442	0.3513
0.4	0.3544	0.1191	0.1783
0.5	0	0	0
0.6	0	0	0