Table 2: 

Model performance (accuracy) on the idiom and simile discriminative tasks. * Difference is significant (α < 0.07) between the supervised and knowledge-enhanced models via t-test.

MethodModelIdiomSimile
Majority 50.0 50.8 
Zero-shot GPT2-XL 53.6 53.7 
GPT3 60.2 62.4 
UnifiedQA 67.7 60.6 
Few-shot GPT3 54.1 51.7 
PET 66.1 55.2 
Supervised RoBERTa 82.0 80.4 
-narrative 65.0 67.9 
Knowledge Context 82.8 79.9 
Enhanced Literal 83.5* 80.6 
Human Performance 92.0 95.0 
MethodModelIdiomSimile
Majority 50.0 50.8 
Zero-shot GPT2-XL 53.6 53.7 
GPT3 60.2 62.4 
UnifiedQA 67.7 60.6 
Few-shot GPT3 54.1 51.7 
PET 66.1 55.2 
Supervised RoBERTa 82.0 80.4 
-narrative 65.0 67.9 
Knowledge Context 82.8 79.9 
Enhanced Literal 83.5* 80.6 
Human Performance 92.0 95.0 
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