Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning

TL;DR

This paper proposes enhancing code modeling by integrating concept graphs with pretrained language models, aiming to leverage high-level domain relationships for improved software engineering tasks.

Contribution

It introduces a novel approach of combining concept graphs with language models to better capture relationships in code for software engineering.

Findings

Preliminary results show improved code search effectiveness.

Joint-learning with concept graphs enhances model understanding.

Encourages further exploration of multi-modal learning in code modeling.

Abstract

The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model architectures. Nevertheless, we believe that the current state-of-the-art does not focus enough on the full potential that data may bring to a learning process in software engineering. Our vision articulates on the idea of leveraging multi-modal learning approaches to modeling the programming world. In this paper, we investigate one of the underlying idea of our vision whose objective based on concept graphs of identifiers aims at leveraging high-level relationships between domain concepts manipulated through particular language constructs. In particular, we propose to enhance an existing pretrained language model of code by joint-learning it with a graph neural network based on our concept graphs. We conducted a preliminary evaluation that shows gain of effectiveness of the models for code search using a simple joint-learning method and prompts us to further investigate our research vision.