Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate that explanations achieve this goal? Some research argues that explanations should help teach a student (either human or machine) to simulate the model being explained, and that the quality of explanations can be measured by the simulation accuracy of students on unexplained examples. In this work, leveraging meta-learning techniques, we extend this idea to improve the quality of the explanations themselves, specifically by optimizing explanations such that student models more effectively learn to simulate the original model. We train models on three natural language processing and computer vision tasks, and find that students trained with explanations extracted with our framework are able to simulate the teacher significantly more effectively than ones produced with previous methods. Through human annotations and a user study, we further find that these learned explanations more closely align with how humans would explain the required decisions in these tasks. Our code is available at https://github.com/coderpat/learning-scaffold
翻译:现代机器学习模型是不透明的,因此,在解释这些模型行为的方法方面,出现了一个新兴的学术子领域,解释这些模型的行为。然而,提供这种解释的准确目标是什么,我们如何能证明解释这个目标?一些研究认为,解释应该帮助教育学生(人或机器)模拟正在解释的模型,而解释的质量可以通过学生在解释性实例上的模拟准确性来衡量。在这项工作中,利用元学习技术,我们推广这一想法,以提高解释本身的质量,特别是优化解释,使学生模型能够更有效地学习模拟原始模型。我们培训三种自然语言处理和计算机视觉任务的模型,发现以我们框架进行解释训练的学生能够比用以前的方法模拟教师。我们通过人类说明和用户研究发现,这些学到的解释与人类如何解释这些任务中所需的决定更加接近。我们的代码可以在 https://github.com/cderpat/learning-scafold查阅。