CAREER:Understanding Program Comprehension for Automated Software Documentation Generation

这个研究项目的目标是1)创建一个软件开发专业人员如何编写软件文档的程序理解模型，以及2)使用该模型设计算法来自动化编写文档的过程。在软件开发项目中，编写文档的过程是一项主要的开销，而且经常被忽略。通过自动化过程的关键组件，这项研究可以帮助程序员避免这些费用，从而提高生产力。该项目研究了程序员在阅读源代码以编写文档时遵循的过程。然后，该项目提出了模拟该过程的算法。这些算法与新颖的自然语言生成系统相结合，以创建软件行为的描述。然后将这些描述集成到源代码的文档中。这个项目的一个关键的更广泛的影响是增加了视力障碍者的劳动力参与。首先，研究产生的描述可以用于盲人程序员的无障碍技术，帮助盲人程序员阅读源代码。第二，为盲人和视障儿童开设的国家K-12学校的扩展项目帮助这些学校的学生为软件开发行业的职业生涯做好准备。

The objective of this research project is 1) to create a model of program comprehension for how software development professionals write software documentation, and 2) to use this model to design algorithms to automate the process of writing documentation. The process of writing documentation is a major expense in software development projects, and is often neglected. By automating key components of the process, this research helps programmers to avoid this expense and therefore to be more productive.The project studies the process that programmers follow when reading source code to write documentation. Then, the project proposes algorithms to mimic that process. These algorithms are integrated with novel natural language generation systems to create descriptions of software behavior. These descriptions are then integrated into documentation of the source code. A key broader impact of this project is to increase the workforce participation of persons with visual disabilities. First, the descriptions generated by the research can be used in accessibility technologies for blind programmers, to help those programmers read source code. Second, an outreach program to state K-12 schools for the blind and visually impaired helps prepare students in these schools prepare for a career in the software development industry.