Skip to Main Content
Table 5: 
Results on multi-segment sentences, where each sentence contains multiple targets or multiple mentions of the same target. TG-SAN outperforms its degenerated version and the baseline model, showing the advantage of the proposed structured attention mechanism in uncovering multiple target-related contexts.
ModelTweetLaptopRestaurant
AccuracyMacro-F1AccuracyMacro-F1AccuracyMacro-F1
w/o SCU & CFU 0.6316 0.5250 0.6937 0.6415 0.8097 0.6995 
TG-SAN (r = 1) 0.6842 0.5667 0.7487 0.6946 0.8230 0.7213 
 
TG-SAN 0.7368 0.6850 0.7513 0.7114 0.8291 0.7366 
ModelTweetLaptopRestaurant
AccuracyMacro-F1AccuracyMacro-F1AccuracyMacro-F1
w/o SCU & CFU 0.6316 0.5250 0.6937 0.6415 0.8097 0.6995 
TG-SAN (r = 1) 0.6842 0.5667 0.7487 0.6946 0.8230 0.7213 
 
TG-SAN 0.7368 0.6850 0.7513 0.7114 0.8291 0.7366 
Close Modal

or Create an Account

Close Modal
Close Modal