Trends in Explanations: Understanding and Debugging Data-driven Systems
Trends in Explanations: Understanding and Debugging Data-driven Systems
复制标题
DOI：
10.1561/1900000074
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Boris Glavic;A. Meliou;Sudeepa Roy
中科院分区：
文献类型：
--
作者：
Boris Glavic;A. Meliou;Sudeepa Roy
人类通过寻求理解事物发生的原因和方式来推断周围的世界。同样的原则也适用于许多人类活动日益依赖的技术。信任、透明度和可理解性问题对于促进系统的采用和正确使用至关重要。然而，随着我们使用的系统和技术的日益复杂，很难甚至不可能理解它们的功能和行为，并且仅仅通过手工调查来证明令人惊讶的观察结果是正确的。解释支持可以简化人类与技术的交互：解释可以帮助用户理解系统的功能，证明系统的结果，并增加他们对自动化决策的信任。本文的目标是通过识别不同问题设置和解决方案之间的共性，概述在数据驱动流程的解释支持方面的现有工作。我们建议在三个维度上对可解释性要求进行分类：解释的目标（“什么”），Boris Glavic， Alexandra Meliou和Sudeepa Roy（2021）的受众，“解释的趋势：理解和调试数据驱动系统”，数据库的基础和趋势®：第11卷，第3期，第226-318页。DOI: 10.1561 / 1900000074。记录的版本可在：http://dx.doi.org/10.1561/1900000074
Humans reason about the world around them by seeking to understand why and how something occurs. The same principle extends to the technology that so many of human activities increasingly rely on. Issues of trust, transparency, and understandability are critical in promoting adoption and proper use of systems. However, with increasing complexity of the systems and technologies we use, it is hard or even impossible to comprehend their function and behavior, and justify surprising observations through manual investigation alone. Explanation support can ease humans’ interactions with technology: explanations can help users understand a system’s function, justify system results, and increase their trust in automated decisions. Our goal in this article is to provide an overview of existing work in explanation support for data-driven processes, through a lens that identifies commonalities across varied problem settings and solutions. We suggest a classification of explainability requirements across three dimensions: the target of the explanation (“What”), the audience of the Boris Glavic, Alexandra Meliou and Sudeepa Roy (2021), “Trends in Explanations: Understanding and Debugging Data-driven Systems”, Foundations and Trends® in Databases: Vol. 11, No. 3, pp 226–318. DOI: 10.1561/1900000074. The version of record is available at: http://dx.doi.org/10.1561/1900000074