Table 6: 
Final prediction F1 score of our model on the auxiliary story classification task in terms of the four types of story sets respectively, and the proportional distribution of the predicted story types of the generated stories by different models.
Story typesD1D2D3D4
F1 score 0.80 0.81 0.88 0.98 
 
Models Proportional Distribution (%) 
GPT-2 (Pretrain) 15.83 40.8 39.36 4.01 
GPT-2 (Fine-tune) 86.94 9.98 2.93 0.15 
 
Ours 90.12 7.98 1.86 0.04 
 w/o Knowledge 87.76 9.51 2.67 0.06 
 w/o Multi-task 88.69 9.07 2.02 0.22 
Story typesD1D2D3D4
F1 score 0.80 0.81 0.88 0.98 
 
Models Proportional Distribution (%) 
GPT-2 (Pretrain) 15.83 40.8 39.36 4.01 
GPT-2 (Fine-tune) 86.94 9.98 2.93 0.15 
 
Ours 90.12 7.98 1.86 0.04 
 w/o Knowledge 87.76 9.51 2.67 0.06 
 w/o Multi-task 88.69 9.07 2.02 0.22 
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. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept