Code Summarization with Abstract Syntax Tree

Code summarization, which provides a high-level description of the function implemented by code, plays a vital role in software maintenance and code retrieval. Traditional approaches focus on retrieving similar code snippets to generate summaries, and recently researchers pay increasing attention to leverage deep learning approaches, especially the encoder-decoder framework. Approaches based on encoder-decoder suffer from two drawbacks: (a) Lack of summarization in functionality level; (b) Code snippets are always too long (more than ten words), regular encoders perform poorly. In this paper, we propose a novel code representation with the help of Abstract Syntax Trees, which could describe the functionality of code snippets and shortens the length of inputs. Based on our proposed code representation, we develop Generative Task, which aims to generate summary sentences of code snippets. Experiments on large-scale real-world industrial Java projects indicate that our approaches are effective and outperform the state-of-the-art approaches in code summarization.