Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world. In several domains, such as healthcare, such technology has significant potential to reduce the burden on humans by providing quality assistance at scale. However, current methods rely on the traditional pipeline of predicting labels from data, thus completely ignoring the process and guidelines used to obtain the labels. Furthermore, post hoc explanations on the data to label prediction using explainable AI (XAI) models, while satisfactory to computer scientists, leave much to be desired to the end-users due to lacking explanations of the process in terms of human-understandable concepts. We \textit{introduce}, \textit{formalize}, and \textit{develop} a novel Artificial Intelligence (A) paradigm -- Process Knowledge-infused Learning (PK-iL). PK-iL utilizes a structured process knowledge that explicitly explains the underlying prediction process that makes sense to end-users. The qualitative human evaluation confirms through a annotator agreement of 0.72, that humans are understand explanations for the predictions. PK-iL also performs competitively with the state-of-the-art (SOTA) baselines.
翻译:改善深层次学习算法的性能和自然语言解释是人类在现实世界中采用的一个优先事项。在保健等若干领域,这种技术通过大规模提供质量援助,具有减少人类负担的巨大潜力。然而,目前的方法依靠的是传统管道,从数据中预测标签,从而完全无视用于获取标签的过程和准则。此外,对数据进行特别解释,用可解释的AI(XAI)模型来标签预测数据,虽然计算机科学家感到满意,但由于在人类无法理解的概念方面缺乏对过程的解释,最终使用者仍有很多期望。我们\ textitit{intucuce},\textit{croduce},\textit{clizalization},和\textit{de{developing a 人工智能(A) 样板 -- -- 程序知识化学习(PK-iL)。 PK-iL利用一种结构化的过程知识,明确解释对终端用户来说有意义的基本预测过程。定性人类评价通过0.72的注释协议确认,人类能够理解预测的基线(PK-SO-Li) 和TA(SO-SO-SO-SO-SA)的解释。