04/07/2020

A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle

Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen

Keywords: Chinese parsing, rhetorical recognition, Shift-Reduce Parser, Robust Oracle

Abstract Paper Similar Papers

Abstract: This work proposes a standalone, complete Chinese discourse parser for practical applications. We approach Chinese discourse parsing from a variety of aspects and improve the shift-reduce parser not only by integrating the pre-trained text encoder, but also by employing novel training strategies. We revise the dynamic-oracle procedure for training the shift-reduce parser, and apply unsupervised data augmentation to enhance rhetorical relation recognition. Experimental results show that our Chinese discourse parser achieves the state-of-the-art performance.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACL 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
 9:39 
 0
 0
 0
 0
 8:52 
 0
 0
 0
 0
 11:07 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 6:13 
 0
 0
 0
 0
 8:35 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 5:38 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 11:53 
 0
 0
 0
 0
 9:17 
 0
 0
 0
 0
 8:39 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 6:03 
 0
 0
 0
 0
 14:10 
 0
 0
 0
 0
 7:38 
 0
 0
 0
 0
 14:01 
 0
 0
 0
 0
 16:18 
 0
 0
 0
 0
 10:45 
 0
 0
 0
 0
 11:34 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 13:49 
 0
 0
 0
 0
 6:15 
 0
 0
 0
 0
 13:23 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 11:35 
 0
 0
 0
 0
 7:22 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 11:29 
 0
 0
 0
 0
 7:44 
 0
 0
 0
 0
 8:03 
 0
 0
 0
 0
 11:14 
 0
 0
 0
 0
 12:43 
 0
 0
 0
 0
 15:11 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 0
 8:15 
 0
 0
 0
 0
 7:54 
 0
 0
 0
 0
 14:22