no code implementations • 29 Sep 2021 • Guanhua Zheng, Jitao Sang, Wang Haonan, Changsheng Xu
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).
1 code implementation • 24 Apr 2020 • Wang Haonan, Gao Yang, Bai Yu, Mirella Lapata, Huang Heyan
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.