19/04/2021

How fast can BERT learn simple natural language inference?

Yi-Chung Lin, Keh-Yih Su

Keywords:

Abstract Paper Similar Papers

Abstract: This paper empirically studies whether BERT can really learn to conduct natural language inference (NLI) without utilizing hidden dataset bias; and how efficiently it can learn if it could. This is done via creating a simple entailment judgment case which involves only binary predicates in plain English. The results show that the learning process of BERT is very slow. However, the efficiency of learning can be greatly improved (data reduction by a factor of 1,500) if task-related features are added. This suggests that domain knowledge greatly helps when conducting NLI with neural networks.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at EACL 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 11:12 
 0
 0
 0
 0
 9:11 
 0
 0
 0
 0
 13:57 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 6:59 
 0
 0
 0
 0
 10:51 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 6:38 
 0
 0
 0
 0
 11:01 
 0
 0
 0
 0
 13:50 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 8:58 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 12:15 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 10:27 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 6:56 
 0
 0
 0
 0
 5:59 
 0
 0
 0
 0
 12:12 
 0
 0
 0
 0
 12:22 
 0
 0
 0
 0
 9:54 
 0
 0
 0
 0
 12:50 
 0
 0
 0
 0
 6:26 
 0
 0
 0
 0
 10:20 
 0
 0
 0
 0
 6:24 
 0
 0
 0
 0
 11:55 
 0
 0
 0
 0
 10:28 
 0
 0
 0
 0
 11:46 
 0
 0
 0
 0
 13:55 
 0
 0
 0
 0
 11:54 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 10:16 
 0
 0
 0
 0
 3:17