.png){kind=icon}
.png){kind=icon}
Return
GT-SimNet: Improving code automatic summarization via multi-modal similarity networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jss.2022.111495.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Code summarization aims to generate high-quality functional summaries of code snippets to improve the efficiency of program development and maintenance. It is a pressing challenge for code summariza-tion models to capture more comprehensive code knowledge by integrating the feature correlations between the semantics and syntax of the code. In this paper, we propose a multi-modal similarity network based code summarization method: GT-SimNet. It proposes a novel code semantic modelling method based on a local application programming interface (API) dependency graph (Local-ADG), which exhibits an excellent ability to mask irrelevant semantics outside the current code snippet. For code feature fusion, GT-SimNet uses the SimNet network to calculate the correlation coefficients between Local-ADG and abstract syntax tree (AST) nodes and performs fusion under the influence of the correlation coefficients. Finally, it completes the prediction of the target summary by the generator. We conduct extensive experiments to evaluate the performance of GT-SimNet on two language datasets (Java and Solidity). The results show that GT-SimNet achieved BLEU scores of 38.73% and 41.36% on the two datasets, 1.47%similar to 2.68% higher than the best existing baseline. Importantly, GT-SimNet reduces the BLEU scores by 7.28% after removing Local-ADG. This indicates that Local-ADG is effective for the semantic representation of the code.(c) 2022 Elsevier Inc. All rights reserved.
Keywords:
Code summarization
Local API dependency graph
AST
GCN
Journal
IF:
4.1
Papers:
5.4K
Citations:
8.4K