Revisiting File Context for Source Code Summarization

TL;DR

This paper explores enhancing source code summarization by incorporating file context into neural models, demonstrating improvements especially on challenging examples where traditional methods fall short.

Contribution

The paper introduces a novel Transformer-based approach that encodes file context, improving code summarization performance over existing methods.

Findings

File context improves summarization on difficult examples.

The proposed model outperforms baseline approaches.

Encoding file context captures additional relevant information.

Abstract

Source code summarization is the task of writing natural language descriptions of source code. A typical use case is generating short summaries of subroutines for use in API documentation. The heart of almost all current research into code summarization is the encoder-decoder neural architecture, and the encoder input is almost always a single subroutine or other short code snippet. The problem with this setup is that the information needed to describe the code is often not present in the code itself -- that information often resides in other nearby code. In this paper, we revisit the idea of ``file context'' for code summarization. File context is the idea of encoding select information from other subroutines in the same file. We propose a novel modification of the Transformer architecture that is purpose-built to encode file context and demonstrate its improvement over several baselines. We find that file context helps on a subset of challenging examples where traditional approaches struggle.