MIT Press

Skip to Main Content

Table 7:

Accuracy (Acc) and average F1 (Avg F1) on tweet classification (hashtags as labels). CNN only: CNN without using our representations. Seperate-Train: CNN fed with our pre-trained representations. Joint-Train: Joint training CNN and our model.

Models	TREC		TWT16
	Acc	Avg F1	Acc	Avg F1
CNN only	0.199	0.167	0.334	0.311
Separate-Train	0.284	0.270	0.391	0.390
Joint-Train	0.297	0.286	0.428	0.413

Models	TREC		TWT16
	Acc	Avg F1	Acc	Avg F1
CNN only	0.199	0.167	0.334	0.311
Separate-Train	0.284	0.270	0.391	0.390
Joint-Train	0.297	0.286	0.428	0.413