CRaDLe: Deep code retrieval based on semantic Dependency Learning. (September 2021)

• Record Type: Journal Article
• Authors: Gu, Wenchao; Li, Zongjie; Gao, Cuiyun; Wang, Chaozheng; Zhang, Hongyu; Xu, Zenglin; Lyu, Michael R.
• Is Part Of: Neural networks. Volume 141(2021)
• Page Start: 385
• Page End: 394
• Publication Date: 2021-09
• Subjects: Code retrieval -- Semantic dependency -- Dependency learning -- Neural network; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.04.019
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Code retrieval is a common practice for programmers to reuse existing code snippets in the open-source repositories. Given a user query (i.e., a natural language description), code retrieval aims at searching the most relevant ones from a set of code snippets. The main challenge of effective code retrieval lies in mitigating the semantic gap between natural language descriptions and code snippets. With the ever-increasing amount of available open-source code, recent studies resort to neural networks to learn the semantic matching relationships between the two sources. The statement-level dependency information, which highlights the dependency relations among the program statements during the execution, reflects the structural importance of one statement in the code, which is favorable for accurately capturing the code semantics but has never been explored for the code retrieval task. In this paper, we propose CRaDLe, a novel approach for C ode R etrieval based on statement-level sema ntic D ependency Le arning. Specifically, CRaDLe distills code representations through fusing both the dependency and semantic information at the statement level, and then learns a unified vector representation for each code and description pair for modeling the matching relationship. Comprehensive experiments and analysis on real-world datasets show that the proposed approach can accurately retrieve code snippets for a given query and significantly outperform the state-of-the-art approaches on the task.