Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables

TL;DR

This paper introduces a neuro-symbolic framework for top-down automated software development in limited scopes, leveraging code taxonomy and a semantic pyramid to improve code generation by integrating domain knowledge and hierarchy awareness.

Contribution

It proposes a novel semantic pyramid framework and code taxonomy to enhance neural code generation with hierarchical and domain knowledge in limited scope projects.

Findings

Framework effectively integrates domain knowledge into code generation.

Hierarchical semantic pyramid improves code abstraction understanding.

Preliminary applications confirm the framework's potential.

Abstract

Deep code generation is a topic of deep learning for software engineering (DL4SE), which adopts neural models to generate code for the intended functions. Since end-to-end neural methods lack domain knowledge and software hierarchy awareness, they tend to perform poorly w.r.t project-level tasks. To systematically explore the potential improvements of code generation, we let it participate in the whole top-down development from \emph{expressibles} to \emph{executables}, which is possible in limited scopes. In the process, it benefits from massive samples, features, and knowledge. As the foundation, we suggest building a taxonomy on code data, namely code taxonomy, leveraging the categorization of code information. Moreover, we introduce a three-layer semantic pyramid (SP) to associate text data and code data. It identifies the information of different abstraction levels, and thus introduces the domain knowledge on development and reveals the hierarchy of software. Furthermore, we propose a semantic pyramid framework (SPF) as the approach, focusing on software of high modularity and low complexity. SPF divides the code generation process into stages and reserves spots for potential interactions. In addition, we conceived preliminary applications in software development to confirm the neuro-symbolic framework.