arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01566cs.SEcs.LGcs.PL
收藏

面向有限范围内的自顶向下自动化开发:从可表达内容到可执行代码的神经符号框架

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

Monash University(蒙纳士大学);University of Zurich(苏黎世大学)

Jian Gu, Harald C. Gall

AI总结:

针对端到端神经代码生成方法在项目级任务中表现不佳的问题,提出融合代码分类法、三层语义金字塔的神经符号SPF框架,支持有限范围内从可表达内容到可执行代码的自顶向下自动化开发。

摘要:

深度代码生成是深度学习赋能软件工程(DL4SE)领域的一个研究方向,其采用神经模型为预期功能生成代码。由于端到端神经方法缺乏领域知识和软件层级感知能力,它们在项目级任务上的表现往往较差。为系统性地探索代码生成的潜在提升空间,我们让代码生成参与从“可表达内容”到“可执行代码”的完整自顶向下开发流程,这一模式在有限范围内具备可行性。在此过程中,代码生成可从海量样本、特征与知识中获益。作为基础,我们建议利用代码信息的分类体系,构建代码数据的分类学即代码分类法。此外,我们引入三层语义金字塔(SP)以关联文本数据与代码数据,它可识别不同抽象层级的信息,从而引入开发领域知识并展现软件的层级结构。进一步地,我们提出语义金字塔框架(SPF)作为实现方案,聚焦于高模块化、低复杂度的软件。SPF将代码生成过程划分为多个阶段,并为潜在的交互预留了节点。另外,我们构思了该框架在软件开发中的初步应用,以验证这一神经符号框架的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑