A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the potential harms associated with the lack of understanding of the models' rationales include privacy violations, adversarial manipulations, and unfair discrimination. As a result, the accountability and transparency of ML models have been posed as critical desiderata by works in policy and law, philosophy, and computer science. In computer science, the decision-making process of ML models has been studied by developing accountability and transparency methods. Accountability methods, such as adversarial attacks and diagnostic datasets, expose vulnerabilities of ML models that could lead to malicious manipulations or systematic faults in their predictions. Transparency methods explain the rationales behind models' predictions gaining the trust of relevant stakeholders and potentially uncovering mistakes and unfairness in models' decisions. To this end, transparency methods have to meet accountability requirements as well, e.g., being robust and faithful to the underlying rationales of a model. This thesis presents my research that expands our collective knowledge in the areas of accountability and transparency of ML models developed for complex reasoning tasks over text.

事实检查系统已成为验证假冒误导性新闻的重要工具。当人类可读的解释陪真实性标签，这些系统变得更值得信赖。然而，这样的解释人工收集是昂贵的和耗时的。最近的作品帧解释代采掘总结，并提出从专业记者的执政评论（RCS）自动选择最重要的事实有足够的子集，以获得事实查证的解释。然而，这些解释缺乏流畅性和连贯的句子。在这项工作中，我们提出了一个迭代编辑为基础的算法只使用短语级的编辑进行断开驻地协调员监督的后期编辑。为了规范我们的加工算法，我们使用的组件，包括流畅性和语义保留一个计分函数。此外，我们显示我们的方法在完全无人监管环境的适用性。我们有两个标准数据集实验，LIAR-PLUS和PubHealth。我们表明，我们的模型生成的流畅，可读性强，非冗余的解释，并覆盖的事实检查的重要信息。