02/02/2021

Multi-Dimensional Explanation of Target Variables from Documents

Diego Antognini, Claudiu Musat, Boi Faltings

Keywords:

Abstract Paper Similar Papers

Abstract: Automated predictions require explanations to be interpretable by humans. Past work used attention and rationale mechanisms to find words that predict the target variable of a document. Often though, they result in a tradeoff between noisy explanations or a drop in accuracy. Furthermore, rationale methods cannot capture the multi-faceted nature of justifications for multiple targets, because of the non-probabilistic nature of the mask. In this paper, we propose the Multi-Target Masker (MTM) to address these shortcomings. The novelty lies in the soft multi-dimensional mask that models a relevance probability distribution over the set of target variables to handle ambiguities. Additionally, two regularizers guide MTM to induce long, meaningful explanations. We evaluate MTM on two datasets and show, using standard metrics and human annotations, that the resulting masks are more accurate and coherent than those generated by the state-of-the-art methods. Moreover, MTM is the first to also achieve the highest F1 scores for all the target variables simultaneously.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949254
(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
 13:14 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 11:58 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 1
 12:41 
 0
 0
 0
 0
 15:05 
 0
 0
 0
 0
 7:10 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 11:54 
 0
 0
 0
 0
 5:56 
 0
 0
 0
 0
 16:40 
 0
 0
 0
 0
 11:01 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 11:11 
 0
 0
 1
 0
 12:19 
 0
 0
 0
 1
 12:13 
 0
 0
 0
 0
 12:57 
 0
 0
 0
 0
 11:52 
 0
 0
 0
 0
 11:53 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 10:42 
 0
 0
 0
 0
 11:31 
 0
 0
 0
 0
 10:12 
 0
 0
 0
 0
 18:55 
 0
 0
 0
 0
 18:56 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 10:42 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 6:05 
 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 9:41 
 0
 0
 0
 0
 19:28 
 0
 0
 0
 0
 12:17 
 0
 0
 0
 0
 8:50 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 12:05 
 0
 0
 0
 0
 0:58