Abstract
Given a bug report, bug localization technique can help developers automatically locate potential buggy files. Information retrieval and deep learning approaches have been applied in bug localization by extracting lexical features in bug reports and syntactic features in source code files, though they fail to utilize the structural and semantic information of source code files. In this paper, we present a bug localization system CAST, which exploits deep learning and customized abstract syntax trees of programs to locate potential buggy source files automatically and effectively. Specifically, CAST extracts both lexical semantics in bug reports (e.g., words) and source files (e.g., method names) and program semantics in source files (e.g., abstract syntax tree, AST). Moreover, CAST enhances the tree-based convolutional neural network (TBCNN) model with customized ASTs, which distinguish between user-defined methods and system-provided ones to reflect their contributions leading to defects. Furthermore, customized ASTs group the syntactic entities with similar semantics and prune the ones with little or redundant semantics in order to facilitate the learning performance. Experimental results on four widely-used software projects show that CAST significantly outperforms the state-of-the-art methods in locating the buggy source files.
Highlights
For large and evolving software, developers may receive a large number of bug reports, and it is difficult and costly to manually locate the potential buggy source files based on bug reports
EVALUATION To evaluate the performance of CAST, we focus on four research questions (RQ) as follows: RQ1 What effect do the different model settings have on CAST? When building CAST, we need to determine the suitable values of hyper-parameters
RQ2 Can CAST outperform other bug localization methods? To evaluate the capability of CAST, we compare CAST with four state-of-the-art tools in bug localization (BugLocator [28], DNNLOC [29], DeepLocator [35], NP-convolutional neural network (CNN) [22])
Summary
For large and evolving software, developers may receive a large number of bug reports, and it is difficult and costly to manually locate the potential buggy source files based on bug reports. Liang et al.: Deep Learning With Customized Abstract Syntax Tree for Bug Localization These tools can model natural and programming language for bug localization, there is room for improvement on accuracy and performance. CAST leverages CNN to extract rich lexical semantic features, which indicate the relationship between syntactic entities, e.g. words or methods in bug reports and source files, and exploits TBCNN [9] on customized ASTs to capture hierarchical structure features, which contain the structural or semantic relation of program statements in source code files. It differentiates user-defined methods and system-provided ones to reflect their contributions leading to defects, which is helpful to improve the accuracy of bug localization It groups the syntactic entities with similar semantics and prunes the ones with little or redundant semantics to facilitate the learning performance.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
