Auditing Deep Learning processes through Kernel-based Explanatory Models
While NLP systems become more pervasive, their accountability gains value as a focal point of effort. Epistemological opaqueness of nonlinear learning methods, such as deep learning models, can be a major drawback for their adoptions. In this paper, we discuss the application of Layerwise Relevance Propagation over a linguistically motivated neural architecture, the Kernel-based Deep Architecture, in order to trace back connections between linguistic properties of input instances and system decisions. Such connections then guide the construction of argumentations on network{'}s inferences, i.e., explanations based on real examples, semantically related to the input. We propose here a methodology to evaluate the transparency and coherence of analogy-based explanations modeling an audit stage for the system. Quantitative analysis on two semantic tasks, i.e., question classification and semantic role labeling, show that the explanatory capabilities (native in KDAs) are effective and they pave the way to more complex argumentation methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningSemantic Role LabelingSimilar Papers 제목 키워드 기반
Auditing Differential Privacy in High Dimensions with the Kernel Quantum Rényi Divergence
Differential privacy (DP) is the de facto standard for private data release and private machine learning. Auditing black-box DP algorithms and mechanisms to certify whether they satisfy a certain DP guarantee is challeng…
Bayesian Approximate Kernel Regression with Variable Selection
Nonlinear kernel regression models are often used in statistics and machine learning because they are more accurate than linear models. Variable selection for kernel regression models is a challenge partly because, unlik…
Binary ClassificationregressionVariable SelectionBound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
Bias evaluation benchmarks and dataset and model documentation have emerged as central processes for assessing the biases and harms of artificial intelligence (AI) systems. However, these auditing processes have been cri…
The Necessity of AI Audit Standards Boards
Auditing of AI systems is a promising way to understand and manage ethical problems and societal risks associated with contemporary AI systems, as well as some anticipated future risks. Efforts to develop standards for a…
Decoupled Kernel Neural Processes: Neural Network-Parameterized Stochastic Processes using Explicit Data-driven Kernel
Neural Processes (NPs) are a class of stochastic processes parametrized by neural networks. Unlike traditional stochastic processes (e.g., Gaussian processes), which require specifying explicit kernel functions, NPs impl…
DiversityGaussian Processes