论文标题
数据管理和机器学习中的基于分数的解释
Score-Based Explanations in Data Management and Machine Learning
论文作者
论文摘要
我们描述了一些解释方法，以了解数据管理和机器学习中的结果。它们基于将数值得分分配给预定义的和潜在相关的输入。更具体地说，我们考虑了数据库中查询答案的解释，以及分类模型的结果。所描述的方法主要是因果关系和反事实性质。我们主张需要将领域和语义知识带入分数计算。并提出一些做到这一点的方法。
We describe some approaches to explanations for observed outcomes in data management and machine learning. They are based on the assignment of numerical scores to predefined and potentially relevant inputs. More specifically, we consider explanations for query answers in databases, and for results from classification models. The described approaches are mostly of a causal and counterfactual nature. We argue for the need to bring domain and semantic knowledge into score computations; and suggest some ways to do this.
