02/02/2021

MARTA: Leveraging Human Rationales for Explainable Text Classification

Ines Arous, Ljiljana Dolamic, Jie Yang, Akansha Bhardwaj, Giuseppe Cuccu, Philippe Cudré-Mauroux

Keywords:

Abstract Paper Similar Papers

Abstract: Explainability is a key requirement for text classification in many application domains ranging from sentiment analysis to medical diagnosis or legal reviews. Existing methods often rely on "attention" mechanisms for explaining classification results by estimating the relative importance of input units. However, recent studies have shown that such mechanisms tend to mis-identify irrelevant input units in their explanation. In this work, we propose a hybrid human-AI approach that incorporates human rationales into attention-based text classification models to improve the explainability of classification results. Specifically, we ask workers to provide rationales for their annotation by selecting relevant pieces of text. We introduce MARTA, a Bayesian framework that jointly learns an attention-based model and the reliability of workers while injecting human rationales into model training. We derive a principled optimization algorithm based on variational inference with efficient updating rules for learning MARTA parameters. Extensive validation on real-world datasets shows that our framework significantly improves the state of the art both in terms of classification explainability and accuracy.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948579
(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
 11:24 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 19:21 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 16:11 
 0
 0
 0
 0
 5:43 
 0
 0
 0
 0
 11:18 
 0
 0
 0
 0
 19:54 
 0
 0
 0
 0
 17:06 
 0
 0
 0
 0
 2:28 
 0
 0
 0
 0
 14:02 
 0
 0
 1
 0
 12:19 
 0
 0
 0
 0
 5:34 
 0
 0
 0
 0
 13:41 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 5:18 
 1
 0
 0
 0
 11:29 
 0
 0
 0
 0
 11:07 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 0:59 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 11:58 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 19:55 
 0
 0
 0
 0
 9:25 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 16:40 
 0
 0
 0
 0
 18:49 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 3:27 
 0
 0
 0
 0
 4:51 
 0
 0
 0
 0
 14:45 
 0
 0
 0
 0
 20:38 
 0
 0
 0
 0
 16:44