A Concept-based Abstraction-Aggregation Deep Neural Network for Interpretable Document Classification

04/24/2020
by   Tian Shi, et al.
0

Using attention weights to identify information that is important for models' decision making is a popular approach to interpret attention-based neural networks, which is commonly realized via creating a heat-map for every single document based on attention weights. However, this interpretation method is fragile. In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning importance of keywords for predicted labels across a training corpus based on attention weights. Using this idea as the fundamental building block, we further propose a concept-based explanation method that can automatically learn higher-level concepts and their importance to model prediction task. Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network, which can automatically cluster important keywords during an end-to-end training process. We apply these methods to the document classification task and show that they are powerful in extracting semantically meaningful keywords and concepts. Our consistency analysis results based on an attention-based Naïve Bayes Classifier also demonstrate these keywords and concepts are important for model predictions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/25/2022

Human-Centered Concept Explanations for Neural Networks

Understanding complex machine learning models such as deep neural networ...
research
06/10/2020

Why is Attention Not So Attentive?

Attention-based methods have played an important role in model interpret...
research
05/27/2023

Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs

A concept-based classifier can explain the decision process of a deep le...
research
09/22/2020

Towards Causal Explanation Detection with Pyramid Salient-Aware Network

Causal explanation analysis (CEA) can assist us to understand the reason...
research
01/20/2019

Hierarchical Attentional Hybrid Neural Networks for Document Classification

Document classification is a challenging task with important application...
research
08/13/2019

Attention is not not Explanation

Attention mechanisms play a central role in NLP systems, especially with...
research
09/07/2020

Attention based Writer Independent Handwriting Verification

The task of writer verification is to provide a likelihood score for whe...

Please sign up or login with your details

Forgot password? Click here to reset