02/02/2021

Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization

Yinuo Guo, Hualei Zhu, Zeqi Lin, Bei Chen, Jian-Guang Lou, Dongmei Zhang

Keywords:

Abstract Paper Similar Papers

Abstract: Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revisit iterative back-translation, a simple yet effective semi-supervised method, to investigate whether and how it can improve compositional generalization. In this work: (1) We first empirically show that iterative back-translation substantially improves the performance on compositional generalization benchmarks (CFQ and SCAN). (2) To understand why iterative back-translation is useful, we carefully examine the performance gains and find that iterative back-translation can increasingly correct errors in pseudo-parallel data. (3) To further encourage this mechanism, we propose curriculum iterative back-translation, which better improves the quality of pseudo-parallel data, thus further improving the performance.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948885
(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
 5:07 
 0
 0
 0
 0
 5:58 
 0
 0
 0
 0
 13:24 
 0
 0
 0
 0
 5:34 
 1
 1
 0
 0
 15:22 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 13:35 
 0
 0
 0
 0
 7:32 
 0
 0
 0
 0
 3:09 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 6:03 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 17:42 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 13:41 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 15:22 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 3:54 
 0
 0
 0
 0
 10:18 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:08 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 11:30 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 19:12 
 0
 0
 0
 0
 5:51 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 10:46 
 0
 0
 0
 0
 15:51 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 0
 2:45