Year: 2021
Type: article
Abstract: This paper presents Deepsy, a Natural Language-based synthesizer to assist source code analysis.It takes English descriptions of to-be-found code patterns as its inputs, and automatically produces ASTMatcher expressions that are directly usable by LLVM/Clang to materialize intended code analysis.The code analysis domain features profuse complexities in data types and operations, which make it elusive for prior rule-based synthesizers to tackle.On the other hand, machine learning-based solutions are neither applicable due to the scarcity of well labeled examples.This paper presents how Deepsy addresses the challenges by leveraging deep Natural Language Processing (NLP) and creating a new technique named dependency tree-based co-evolvement.Deepsy features an effective design that seamlessly integrates Natural Language dependency analysis into code analysis and meanwhile synergizes it with type-based narrowing and domain-specific guidance.Deepsy achieves over 70.0%expression-level accuracy and 85.1% individual API-level accuracy, significantly outperforming previous solutions.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1356433355, CSR:Small:Supporting Position Independence and Reusability of Data on Byte-Addressable Non-Volatile Memory, G2145270357, SHF: Medium: Scalable Holistic Autotuning for Software Analytics, G3669113783, G3828580493, G4094752214, G4744444288, G5630301777, G5685548091, Collaborative Research: PPoSS: Planning: Scaling Secure Serverless Computing on Heterogeneous Datacenters, G991281326
OpenAlex ID: W4287548144
