Search Results for author:
Found 2 papers, 1 papers with code
Towards Predictable Feature Attribution: Revisiting and Improving Guided BackPropagation
Recently, backpropagation(BP)-based feature attribution methods have been widely adopted to interpret the internal mechanisms of convolutional neural networks (CNNs), and expected to be human-understandable (lucidity) and faithful to decision-making processes (fidelity).
Exploring Explainable Selection to Control Abstractive Summarization
A novel pair-wise matrix captures the sentence interactions, centrality, and attribute scores, and a mask with tunable attribute thresholds allows the user to control which sentences are likely to be included in the extraction.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
