A Topic Guided Pointer-Generator Model for Generating Natural Language Code Summaries

TL;DR

This paper introduces ToPNN, a neural network model that leverages broader context and topic guidance to improve automatic code summarization, significantly outperforming existing methods on a large Java dataset.

Contribution

The novel ToPNN model incorporates class-level topics and a copy mechanism to enhance code summarization beyond existing neural translation approaches.

Findings

Significant performance improvement over state-of-the-art models

Class topics and copy mechanism positively impact summarization quality

Effective at the method level for Java code

Abstract

Code summarization is the task of generating natural language description of source code, which is important for program understanding and maintenance. Existing approaches treat the task as a machine translation problem (e.g., from Java to English) and applied Neural Machine Translation models to solve the problem. These approaches only consider a given code unit (e.g., a method) without its broader context. The lacking of context may hinder the NMT model from gathering sufficient information for code summarization. Furthermore, existing approaches use a fixed vocabulary and do not fully consider the words in code, while many words in the code summary may come from the code. In this work, we present a neural network model named ToPNN for code summarization, which uses the topics in a broader context (e.g., class) to guide the neural networks that combine the generation of new words and the copy of existing words in code. Based on the model we present an approach for generating natural language code summaries at the method level (i.e., method comments). We evaluate our approach using a dataset with 4,203,565 commented Java methods. The results show significant improvement over state-of-the-art approaches and confirm the positive effect of class topics and the copy mechanism.