Automatic Generation of Pseudocode with Attention Seq2seq Model

Automatic pseudocode generation has become a growing demand for software engineers. However, most code snippets in production environments do not have corresponding pseudocode, because writing comments or textual descriptions of program source code typically consumes a lot of manpower. In this paper, we treat pseudocode generation task as a language translation task which means translating programming code into natural language description, and conduct a sophisticated neural machine translation model, attention seq2seq model, on this task. Experiments on a real-world dataset from an open source Python project reveal that seq2seq model could generate understandable pseudocode for practical usage.