08/12/2020

RANCC: Rationalizing Neural Networks via Concept Clustering

Housam Khalifa Bashier, Mi-Young Kim, Randy Goebel

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a new self-explainable model for Natural Language Processing (NLP) text classification tasks. Our approach constructs explanations concurrently with the formulation of classification predictions. To do so, we extract a rationale from the text, then use it to predict a concept of interest as the final prediction. We provide three types of explanations: 1) rationale extraction, 2) a measure of feature importance, and 3) clustering of concepts. In addition, we show how our model can be compressed without applying complicated compression techniques. We experimentally demonstrate our explainability approach on a number of well-known text classification datasets.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6349-rancc-rationalizing-neural-networks-via-concept-clustering
(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
 12:41 
 0
 0
 0
 0
 11:22 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:44 
 0
 0
 0
 0
 11:53 
 0
 0
 0
 0
 14:11 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 13:46 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 6:51 
 0
 0
 0
 0
 9:08 
 0
 0
 0
 0
 12:03 
 0
 0
 0
 0
 12:06 
 0
 0
 0
 0
 12:00 
 0
 0
 0
 0
 16:10 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 9:14 
 0
 0
 0
 0
 11:56 
 0
 0
 0
 0
 7:41 
 0
 0
 0
 0
 6:04 
 0
 0
 0
 0
 13:22 
 0
 0
 0
 0
 15:43 
 0
 0
 0
 0
 16:17 
 0
 0
 0
 0
 10:38 
 0
 0
 0
 0
 6:31 
 0
 0
 0
 0
 9:49 
 0
 0
 0
 0
 18:52 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 8:30 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 11:39 
 0
 0
 0
 0
 12:09 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 13:47