Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization

These descriptions are called "summaries" and are a key component of software documentation for programmers. A programmer may read a short summary like "takes a screenshot" to quickly understand what a section of code does, without resorting to reading the source code. Despite the usefulness of these summaries, programmers often neglect to write or update them. The result is that automatic source code summarization has long been an appetizing target in software engineering research. The scienti c community has long sought to enable machines to understand code in the way people do, so that those machines can describe code like a person would. A con uence of recent advances in both software engineering and machine learning research is bearing fruit, such that automated code summarization seems almost within reach. In particular, neural source code summarization has held the vanguard of the state of the art since around 2017. Neural code summarization refers to approaches based on neural networks, namely the encoderdecoder architecture [61].