01/07/2020

Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System

Pinzhen Chen, Nikolay Bogoychev, Ulrich Germann

Keywords:

Abstract Paper Similar Papers

Abstract: This paper describes the University of Edinburgh’s neural machine translation systems submitted to the IWSLT 2020 open domain Japanese<span class="tex-math">↔</span>Chinese translation task. On top of commonplace techniques like tokenisation and corpus cleaning, we explore character mapping and unsupervised decoding-time adaptation. Our techniques focus on leveraging the provided data, and we show the positive impact of each technique through the gradual improvement of BLEU.

 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
 9:54 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 14:01 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 10:22 
 0
 0
 0
 0
 10:42 
 0
 0
 0
 0
 7:05 
 0
 0
 0
 0
 13:53 
 0
 0
 0
 0
 5:58 
 0
 0
 0
 0
 7:17 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 8:03 
 0
 0
 0
 0
 11:42 
 0
 0
 0
 0
 6:26 
 0
 0
 0
 0
 13:54 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 15:28 
 0
 0
 0
 0
 17:36 
 0
 0
 0
 0
 13:12 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 14:10 
 0
 0
 0
 0
 14:55 
 0
 0
 0
 0
 9:38 
 0
 0
 0
 0
 10:54 
 0
 0
 0
 0
 8:19 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 13:23 
 0
 0
 0
 0
 11:18 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 6:37 
 0
 0
 0
 0
 14:33 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 8:44 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 14:25