Skip to Main Content
Table 4: 

Results of entity-controlled models using reference entities as the input on the CNN/DM dataset. Our CMDP framework significantly improves the ROUGE scores, QA-F1, and appear % (p < 0.0001, approx. randomization test).

MethodR-1R-2R-LQA-F1Appear %
GRSUM 35.89 15.86 31.96 34.92 76.22 
ROUGEEnt 39.45 20.36 36.78 23.47 83.75 
ControlSum 39.41 19.94 36.55 27.02 74.08 
QueryAtt 38.92 20.38 36.47 25.12 75.10 
SD2 39.43 20.71 36.88 27.23 75.97 
 
PG 37.61 19.27 35.04 23.53 37.96 
PG+CMDP 40.81 20.23 37.56 30.38 86.64 
 
D.GPT2 41.68 22.32 38.85 35.32 82.31 
 
D.GPT2+CMDP 45.00 23.65 41.85 36.00 93.37 
D.GPT2+MDP 45.00 23.50 41.90 35.72 94.46 
MethodR-1R-2R-LQA-F1Appear %
GRSUM 35.89 15.86 31.96 34.92 76.22 
ROUGEEnt 39.45 20.36 36.78 23.47 83.75 
ControlSum 39.41 19.94 36.55 27.02 74.08 
QueryAtt 38.92 20.38 36.47 25.12 75.10 
SD2 39.43 20.71 36.88 27.23 75.97 
 
PG 37.61 19.27 35.04 23.53 37.96 
PG+CMDP 40.81 20.23 37.56 30.38 86.64 
 
D.GPT2 41.68 22.32 38.85 35.32 82.31 
 
D.GPT2+CMDP 45.00 23.65 41.85 36.00 93.37 
D.GPT2+MDP 45.00 23.50 41.90 35.72 94.46 
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