08/12/2020

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation

Jianfeng Liu, Ling Luo, Xiang Ao, Yan Song, Haoran Xu, Jian Ye

Keywords:

Abstract Paper Similar Papers

Abstract: Multi-source neural machine translation aims to translate from parallel sources of information (e.g. languages, images, etc.) to a single target language, which has shown better performance than most one-to-one systems. Despite the remarkable success of existing models, they usually neglect the fact that multiple source inputs may have inconsistencies. Such differences might bring noise to the task and limit the performance of existing multi-source NMT approaches due to their indiscriminate usage of input sources for target word predictions. In this paper, we attempt to leverage the potential complementary information among distinct sources and alleviate the occasional conflicts of them. To accomplish that, we propose a source invariance network to learn the invariant information of parallel sources. Such network can be easily integrated with multi-encoder based multi-source NMT methods (e.g. multi-encoder RNN and transformer) to enhance the translation results. Extensive experiments on two multi-source translation tasks demonstrate that the proposed approach not only achieves clear gains in translation quality but also captures implicit invariance between different sources.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6368-meet-changes-with-constancy-learning-invariance-in-multi-source-translation
(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
 10:18 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 14:18 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 6:09 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 14:45 
 0
 0
 0
 0
 7:18 
 0
 0
 0
 0
 12:15 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 0
 16:06 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 15:33 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 14:05 
 0
 0
 0
 0
 13:42 
 0
 0
 0
 0
 9:29 
 0
 0
 0
 1
 11:32 
 0
 1
 1
 1
 10:55 
 0
 0
 0
 0
 14:45 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 15:59 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 10:17 
 1
 0
 0
 0
 5:11 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:18