Skip to main content
. Author manuscript; available in PMC: 2016 Apr 14.
Published in final edited form as: Adv Neural Inf Process Syst. 2015 Dec;28:919–927.

Table 6.

RCV1 micro- and macro-averaged F on the multi-label task (103 topics) with the LYRL04 split.

models micro-F macro-F extra resource
SVM [16] 81.6 60.7 –
bow-CNN [11] 84.0 64.8 –
bow-CNN w/three tv-embed. 85.7 67.1 Unlabeled data