02/02/2021

Multilingual Transfer Learning for QA using Translation as Data Augmentation

Mihaela Bornea, Lin Pan, Sara Rosenthal, Radu Florian, Avirup Sil

Keywords:

Abstract Paper Similar Papers

Abstract: Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. Our first strategy augments the original English training data with machine translation-generated data. This results in a corpus of multilingual silver-labeled QA pairs that is 14 times larger than the original training set. In addition, we propose two novel strategies, language adversarial training and language arbitration framework, which significantly improve the (zero-resource) cross-lingual transfer performance and result in LM embeddings that are less language-variant. Empirically, we show that the proposed models outperform the previous zero-shot baseline on the recently introduced multilingual MLQA and TyDiQA datasets.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949320
(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
 4:59 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 11:42 
 0
 0
 0
 0
 10:34 
 0
 0
 0
 0
 12:15 
 0
 0
 0
 0
 3:51 
 0
 0
 0
 0
 14:08 
 0
 0
 0
 0
 11:39 
 0
 0
 0
 0
 11:52 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 6:56 
 0
 0
 0
 0
 10:48 
 0
 0
 0
 0
 11:16 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 12:09 
 0
 0
 0
 0
 9:46 
 0
 0
 0
 0
 6:53 
 0
 0
 0
 0
 8:30 
 0
 0
 0
 0
 9:30 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 11:28 
 0
 0
 0
 0
 11:44 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 19:06 
 0
 0
 0
 0
 9:24 
 1
 1
 0
 0
 6:51 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 9:45 
 0
 0
 0
 0
 12:42 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 9:53 
 0
 0
 0
 0
 10:07 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 8:47 
 0
 0
 0
 0
 11:04 
 0
 0
 0
 0
 4:56