ProtoTEx: Explaining Model Decisions with Prototype Tensors
We present ProtoTEx, a novel white-box NLP classification architecture based on prototype networks. ProtoTEx faithfully explains model decisions based on prototype tensors that encode latent clusters of training examples. At inference time, classification decisions are based on the distances between the input text and the prototype tensors, explained via the training examples most similar to the most influential prototypes. We also describe a novel interleaved training algorithm that effectively handles classes characterized by the absence of indicative features. On a propaganda detection task, ProtoTEx accuracy matches BART-large and exceeds BERT-large with the added benefit of providing faithful explanations. A user study also shows that prototype-based explanations help non-experts to better recognize propaganda in online news.
Code (1)
Tasks
modelPropaganda detectionSimilar Papers 제목 키워드 기반
GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classification
Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on text classification tasks with their powerful word embeddings, but their black-box nature, which l…
Graph Attentiontext-classificationText ClassificationWord EmbeddingsExplaining Deep Classification of Time-Series Data with Learned Prototypes
The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induc…
ClassificationDecision MakingGeneral ClassificationTime Series+1Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models
Explaining black-box Artificial Intelligence (AI) models is a cornerstone for trustworthy AI and a prerequisite for its use in safety critical applications such that AI models can reliably assist humans in critical decis…
image-classificationImage ClassificationNeuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models
In this paper, we present a Neuron Abandoning Attention Flow (NAFlow) method to address the open problem of visually explaining the attention evolution dynamics inside CNNs when making their classification decisions. A n…
ClassificationContrastive LearningDecision MakingFew-Shot Image Classification+3This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition
Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image "looks like" a prototype. However, perceptual si…
ClassificationGeneral Classification