SHF: Small: A Theory of Explanation Languages

SHF：小：解释语言理论

• 批准号: 1717300
• 负责人: Martin Erwig
• 金额: $ 49.99万
• 依托单位: Oregon State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1717300&HistoricalAwards=false
• 关键词: SHF; Small; Theory; Explanation; Languages

Trust in a computing system depends on understanding its behavior. When users are confronted with unexpected and unexplained results, they may not be willing to rely on such a system anymore. With computing systems controlling ever-increasing parts of our lives, it is important to ensure that they are accountable and can justify their decisions and actions. For example, we want to know how a decision support system arrived at its suggestion for a particular health-care plan or why a self-driving car could not avoid an accident. Despite this need for understanding computing systems, few systems today explain their behavior to their users. This research explores the nature of explanations and how they can be employed in the creation of computing systems that can explain their behavior to programmers and users. Based on an analysis of the nature of explanations and their properties, this research explores operations for the composition and transformation of explanations and the alignment with computations. Part of the research is the development of criteria to judge the quality of explanations and develop guidelines for the design and implementation of explanation languages. Altogether, this research produces a theory of explanation languages. The development of example explanation languages as suggested by the developed theory and their evaluation according to the explanation quality criteria supports the assessment of the research progress. The broader impact of this project includes support for graduate, undergraduate, and high school students who will carry the ideas developed in this project out into the world. Moreover, a theory of explanations and a framework for systematically adding explanations to computing systems empowers software developers to make their products more widely understandable and trustworthy, which ultimately enhances the acceptance of new technologies in society. This research leads to methods and tools that affect the design of future software. Given the importance of software in all aspects of our lives and the growing need for understanding its behaviors, the middle- and long-term practical impact of this research can be enormous.

对计算系统的信任取决于对其行为的理解。当用户面对意想不到的和无法解释的结果时，他们可能不愿意再依赖这样的系统。随着计算机系统控制着我们生活中越来越多的部分，重要的是要确保它们是负责任的，并且可以证明它们的决定和行动是合理的。例如，我们想知道决策支持系统是如何对特定的医疗保健计划提出建议的，或者为什么自动驾驶汽车无法避免事故。尽管需要理解计算系统，但今天很少有系统向用户解释它们的行为。本研究探讨了解释的本质，以及如何将其应用于能够向程序员和用户解释其行为的计算系统的创建。本研究在分析解释的性质及其性质的基础上，探讨了解释的组成和转换的操作以及与计算的对齐。研究的一部分是制定标准来判断解释的质量，并为解释语言的设计和实施制定指导方针。总之，这项研究产生了一种解释语言理论。根据已发展理论所建议的示例解释语言的发展，以及根据解释质量标准对示例解释语言的评价，支持了对研究进展的评估。这个项目更广泛的影响包括支持研究生、本科生和高中生，他们将把这个项目中发展出来的想法带到世界上。此外，解释理论和系统地向计算系统添加解释的框架使软件开发人员能够使他们的产品更广泛地被理解和信任，这最终提高了社会对新技术的接受程度。这项研究产生了影响未来软件设计的方法和工具。鉴于软件在我们生活的各个方面的重要性，以及对理解其行为的日益增长的需求，这项研究的中期和长期实际影响可能是巨大的。

项目成果

A domain-specific language for exploratory data visualization

用于探索性数据可视化的特定领域语言

• DOI: 10.1145/3278122.3278138
• 发表时间: 2018
• 期刊: 17th ACM SIGPLAN International Conference on Generative Programming: Concepts and Experiences
• 作者: Smeltzer, Karl;Erwig, Martin
• 通讯作者: Erwig, Martin

Explaining Deep Adaptive Programs via Reward Decomposition

通过奖励分解解释深度自适应程序

• 发表时间: 2018
• 期刊: IJCAI/ECAI Workshop on Explainable Artificial Intelligence
• 作者: Erwig, Martin;Fern, Alan;Murali, Magesh;Koul, Anurag
• 通讯作者: Koul, Anurag

Comparative Visualizations through Parameterization and Variability

通过参数化和可变性进行比较可视化

• DOI: 10.1109/vlhcc.2018.8506578
• 发表时间: 2018
• 期刊: 2018 IEEE Symposium on Visual Languages and Human-Centric Computing
• 作者: Smeltzer, Karl;Erwig, Martin
• 通讯作者: Erwig, Martin

Variational Pictures

变体图片

• DOI: 10.1007/978-3-319-91376-6_9
• 发表时间: 2018
• 期刊: Int. Conf. on the Theory and Application of Diagrams
• 作者: Erwig, M.;Smeltzer, K.
• 通讯作者: Smeltzer, K.

Adaptable Traces for Program Explanations

用于程序解释的适应性跟踪

• DOI: 10.1007/978-3-030-89051-3_12
• 发表时间: 2021
• 期刊: Asian Symposium on Programming Languages and Systems
• 作者: Bajaj, Divya;Erwig, Martin;Fedorin, Danila;Gay, Kai
• 通讯作者: Gay, Kai