02/02/2021

REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement

Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang

Keywords:

Abstract Paper Similar Papers

Abstract: When answering a question, people often draw upon their rich world knowledge in addition to the particular context. While recent works retrieve supporting facts/evidence from commonsense knowledge bases to supply additional information to each question, there is still ample opportunity to advance it on the quality of the evidence. It is crucial since the quality of the evidence is the key to answering common- sense questions, and even determines the upper bound on the QA systems’ performance. In this paper, we propose a recursive erasure memory network (REM-Net) to cope with the quality improvement of evidence. To address this, REM-Net is equipped with a module to refine the evidence by recursively erasing the low-quality evidence that does not explain the question answering. Besides, instead of retrieving evidence from existing knowledge bases, REM-Net leverages a pre-trained generative model to generate candidate evidence customized for the question. We conduct experiments on two commonsense question answering datasets, WIQA and CosmosQA. The results demonstrate the performance of REM- Net and show that the refined evidence is explainable.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948520
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 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
 18:24 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 11:53 
 0
 0
 0
 0
 16:31 
 0
 0
 0
 0
 11:58 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 5:51 
 0
 0
 0
 0
 6:50 
 0
 0
 0
 0
 19:10 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 6:16 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 14:33 
 0
 0
 0
 0
 14:15 
 0
 0
 0
 0
 10:28 
 0
 0
 0
 0
 11:50 
 0
 0
 0
 0
 13:32 
 0
 0
 0
 0
 11:55 
 0
 0
 0
 0
 9:25 
 0
 0
 0
 0
 4:19 
 0
 0
 0
 0
 16:14 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 12:47 
 0
 0
 0
 0
 13:57 
 0
 0
 0
 0
 6:54 
 0
 0
 0
 0
 6:17 
 0
 0
 0
 0
 13:14 
 0
 0
 0
 0
 5:55 
 0
 0
 0
 0
 16:06 
 0
 0
 0
 0
 11:39 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 9:04 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 11:58 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 11:56 
 0
 0
 0
 0
 10:42