Embedding API Dependency Graph for Neural Code Generation

TL;DR

This paper introduces ADG-Seq2Seq, a novel approach for neural code generation that models API dependencies as a graph and embeds this structure into a sequence-to-sequence model, significantly improving performance.

Contribution

It proposes a new API dependency graph embedding method integrated into Seq2Seq models for code generation, capturing global API relationships.

Findings

Significant performance improvements over state-of-the-art methods.

Effective API dependency graph embedding enhances code generation.

Robust performance with increasing code length.

Abstract

The problem of code generation from textual program descriptions has long been viewed as a grand challenge in software engineering. In recent years, many deep learning based approaches have been proposed, which can generate a sequence of code from a sequence of textual program description. However, the existing approaches ignore the global relationships among API methods, which are important for understanding the usage of APIs. In this paper, we propose to model the dependencies among API methods as an API dependency graph (ADG) and incorporate the graph embedding into a sequence-to-sequence (Seq2Seq) model. In addition to the existing encoder-decoder structure, a new module named ``embedder" is introduced. In this way, the decoder can utilize both global structural dependencies and textual program description to predict the target code. We conduct extensive code generation experiments on three public datasets and in two programming languages (Python and Java). Our proposed approach, called ADG-Seq2Seq, yields significant improvements over existing state-of-the-art methods and maintains its performance as the length of the target code increases. Extensive ablation tests show that the proposed ADG embedding is effective and outperforms the baselines.