02/02/2021

SALNet: Semi-supervised Few-Shot Text Classification with Attention-based Lexicon Construction

Ju-Hyoung Lee, Sang-Ki Ko, Yo-Sub Han

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a semi-supervised bootstrap learning framework for few-shot text classification. From a small amount of the initial dataset, our framework obtains a larger set of reliable training data by using the attention weights from an LSTM-based trained classifier. We first train an LSTM-based text classifier from a given labeled dataset using the attention mechanism. Then, we collect a set of words for each class called a lexicon, which is supposed to be a representative set of words for each class based on the attention weights calculated for the classification task. We bootstrap the classifier using the new data that are labeled by the combination of the classifier and the constructed lexicons to improve the prediction accuracy. As a result, our approach outperforms the previous state-of-the-art methods including semi-supervised learning algorithms and pretraining algorithms for few-shot text classification task on four publicly available benchmark datasets. Moreover, we empirically confirm that the constructed lexicons are reliable enough and substantially improve the performance of the original classifier.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948896
(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
 11:27 
 0
 0
 0
 0
 5:49 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 1
 5:13 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 2:22 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 1
 10:52 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 10:54 
 0
 0
 0
 0
 5:42 
 0
 1
 1
 1
 3:24 
 0
 0
 0
 0
 11:38 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 3:03 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 12:53 
 0
 0
 0
 0
 3:29 
 0
 0
 0
 0
 13:31 
 0
 0
 0
 0
 17:04 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 15:25 
 0
 0
 0
 0
 9:21 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 14:45 
 0
 0
 0
 0
 2:47 
 0
 0
 0
 0
 2:38 
 0
 0
 0
 0
 10:06 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 14:07 
 0
 0
 0
 0
 6:59 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 12:00 
 0
 0
 0
 0
 4:58