08/12/2020

Multi-choice Relational Reasoning for Machine Reading Comprehension

Wuya Chen, Xiaojun Quan, Chunyu Kit, Zhengcheng Min, Jiahai Wang

Keywords:

Abstract Paper Similar Papers

Abstract: This paper presents our study of cloze-style reading comprehension by imitating human reading comprehension, which normally involves tactical comparing and reasoning over candidates while choosing the best answer. We propose a multi-choice relational reasoning (McR<span class="tex-math"><sup>2</sup></span>) model with an aim to enable relational reasoning on candidates based on fusion representations of document, query and candidates. For the fusion representations, we develop an efficient encoding architecture by integrating the schemes of bidirectional attention flow, self-attention and document-gated query reading. Then, comparing and inferring over candidates are executed by a novel relational reasoning network. We conduct extensive experiments on four datasets derived from two public corpora, Children’s Book Test and Who DiD What, to verify the validity and advantages of our model. The results show that it outperforms all baseline models significantly on the four benchmark datasets. The effectiveness of its key components is also validated by an ablation study.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6154-multi-choice-relational-reasoning-for-machine-reading-comprehension
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 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
 13:27 
 0
 0
 0
 0
 10:51 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 9:49 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 12:49 
 0
 0
 0
 0
 14:08 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 11:03 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 18:50 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 10:12 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 12:44 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 4:45 
 0
 0
 0
 0
 16:10 
 0
 0
 0
 0
 15:47 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:30 
 0
 0
 0
 0
 11:51 
 0
 0
 0
 0
 15:09 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 8:59 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 13:53 
 0
 0
 0
 0
 5:49 
 0
 0
 0
 0
 9:46 
 0
 0
 0
 0
 9:57 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 1:01