SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers
arXiv:2103.12279
Abstract
We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts. SelfExplain augments existing neural classifiers by adding (1) a globally interpretable layer that identifies the most influential concepts in the training set for a given sample and (2) a locally interpretable layer that quantifies the contribution of each local input concept by computing a relevance score relative to the predicted label. Experiments across five text-classification datasets show that SelfExplain facilitates interpretability without sacrificing performance. Most importantly, explanations from SelfExplain show sufficiency for model predictions and are perceived as adequate, trustworthy and understandable by human judges compared to existing widely-used baselines.
References in corpus (14)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Towards A Rigorous Science of Interpretable Machine Learning
- Axiomatic Attribution for Deep Networks
- Teaching Machines to Read and Comprehend
- Learning Important Features Through Propagating Activation Differences
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Understanding Black-box Predictions via Influence Functions
- SmoothGrad: removing noise by adding noise
- Towards Robust Interpretability with Self-Explaining Neural Networks
- e-SNLI: Natural Language Inference with Natural Language Explanations
- Concept Bottleneck Models
- Hierarchical interpretations for neural network predictions
- Differentiable Reasoning over a Virtual Knowledge Base
- Deep Weighted Averaging Classifiers