19/04/2021

Data augmentation for voice-assistant NLU using BERT-based interchangeable rephrase

Akhila Yerukola, Mason Bretan, Hongxia Jin

Keywords:

Abstract Paper Similar Papers

Abstract: We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation techniques encompassing generative models such as VAEs and performance-boosting techniques such as synonym replacement and back-translation. We show our method performs strongly on domain and intent classification tasks for a voice assistant and in a user-study focused on utterance naturalness and semantic similarity.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at EACL 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
 13:58 
 0
 0
 0
 0
 4:03 
 0
 0
 0
 0
 11:16 
 0
 0
 0
 0
 11:07 
 0
 0
 0
 0
 9:50 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 6:45 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 6:52 
 0
 0
 0
 0
 8:17 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 7:16 
 0
 0
 0
 0
 12:55 
 1
 0
 0
 0
 10:06 
 0
 0
 0
 0
 11:16 
 0
 0
 0
 0
 5:51 
 0
 0
 0
 0
 14:01 
 0
 0
 0
 1
 11:06 
 0
 0
 0
 0
 11:15 
 0
 0
 0
 0
 13:21 
 0
 0
 0
 0
 23:36 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 8:51 
 0
 0
 0
 0
 4:50 
 0
 0
 0
 0
 12:08 
 0
 0
 0
 0
 5:34 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 11:56 
 0
 0
 0
 0
 12:00 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 7:46 
 0
 0
 0
 0
 7:34 
 0
 0
 0
 0
 7:41 
 0
 0
 0
 0
 14:34 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 0
 19:20