Skip to Main Content
Table 4: 
Effects of r, the number of structured representations extracted from the context sentence. Results show that capturing multiple contexts (r¿1) is beneficial for TDSA.
r =TweetLaptopRestaurant
AccuracyMacro-F1AccuracyMacro-F1AccuracyMacro-F1
1 0.7399 0.7261 0.7512 0.6998 0.8131 0.7167 
2 0.7471 0.7365 0.7527 0.7118 0.8166 0.7259 
3 0.7355 0.7210 0.7496 0.7063 0.8184 0.7348 
4 0.7399 0.7236 0.7433 0.7028 0.8220 0.7447 
5 0.7327 0.7182 0.7433 0.6972 0.8184 0.7407 
r =TweetLaptopRestaurant
AccuracyMacro-F1AccuracyMacro-F1AccuracyMacro-F1
1 0.7399 0.7261 0.7512 0.6998 0.8131 0.7167 
2 0.7471 0.7365 0.7527 0.7118 0.8166 0.7259 
3 0.7355 0.7210 0.7496 0.7063 0.8184 0.7348 
4 0.7399 0.7236 0.7433 0.7028 0.8220 0.7447 
5 0.7327 0.7182 0.7433 0.6972 0.8184 0.7407 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy.
Accept