01/07/2020

Adversarial Training for Commonsense Inference

Lis Pereira, Xiaodong Liu, Fei Cheng, Masayuki Asahara, Ichiro Kobayashi

Keywords:

Abstract Paper Similar Papers

Abstract: We apply small perturbations to word embeddings and minimize the resultant adversarial risk to regularize the model. We exploit a novel combination of two different approaches to estimate these perturbations: 1) using the true label and 2) using the model prediction. Without relying on any human-crafted features, knowledge bases, or additional datasets other than the target datasets, our model boosts the fine-tuning performance of RoBERTa, achieving competitive results on multiple reading comprehension datasets that require commonsense inference.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACL Workshops 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
 11:49 
 0
 0
 0
 0
 5:26 
 0
 0
 0
 0
 4:13 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 6:53 
 0
 0
 0
 0
 12:14 
 0
 0
 0
 0
 11:34 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 10:27 
 0
 0
 0
 0
 12:19 
 0
 0
 0
 0
 12:53 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 7:55 
 0
 0
 0
 0
 9:04 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 9:16 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 5:37 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 7:55 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 4:48 
 0
 0
 0
 0
 2:30 
 0
 0
 0
 0
 8:19 
 0
 0
 0
 0
 8:12 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 8:58 
 0
 0
 0
 0
 13:57 
 0
 0
 0
 0
 11:45 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 11:39 
 0
 0
 0
 0
 7:33 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 12:03 
 0
 0
 0
 0
 10:57 
 0
 0
 0
 0
 5:15