MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure

Abstract

Code semantics similarity can be used for many tasks such as code recommendation, automated software defect correction, and clone detection. Yet, the accuracy of such systems has not yet reached a level of general purpose reliability. To help address this, we present Machine Inferred Code Similarity (MISIM), a neural code semantics similarity system consisting of two core components: (i)MISIM uses a novel context-aware semantics structure, which was purpose-built to lift semantics from code syntax; (ii)MISIM uses an extensible neural code similarity scoring algorithm, which can be used for various neural network architectures with learned parameters. We compare MISIM to four state-of-the-art systems, including two additional hand-customized models, over 328K programs consisting of over 18 million lines of code. Our experiments show that MISIM has 8.08% better accuracy (using MAP@R) compared to the next best performing system.

arXiv admin note: text overlap with arXiv:2003.11118

References in corpus (11)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Decoupled Weight Decay Regularization
• Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
• Convolutional Neural Networks over Tree Structures for Programming Language Processing
• Neural Code Comprehension: A Learnable Representation of Code Semantics
• LambdaNet: Probabilistic Type Inference using Graph Neural Networks
• How Developers Choose Names
• AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms
• Learning to Represent Programs with Property Signatures
• Toward Code Generation: A Survey and Lessons from Semantic Parsing