Towards Code Summarization of APIs Based on Unofficial Documentation Using NLP Techniques
This addresses the challenge for developers who need better API guidance, though it is incremental as it builds on existing NLP methods for code summarization.
The paper tackles the problem of inefficient official API documentation by proposing an automatic approach to generate summaries from unofficial sources like Stack Overflow and GitHub using NLP techniques, with results showing competitive summaries that can complement existing documentation.
Each programming language comes with official documentation to guide developers with APIs, methods, and classes. However, in some cases, official documentation is not an efficient way to get the needed information. As a result, developers may consult other sources (e.g., Stack Overflow, GitHub) to learn more about an API, its implementation, usage, and other information that official documentation may not provide. In this research, we propose an automatic approach to generate summaries for APIs and methods by leveraging unofficial documentation using NLP techniques. Our findings demonstrate that the generated summaries are competitive, and can be used as a complementary source for guiding developers in software development and maintenance tasks.