.png){kind=icon}
Return
Learning to represent code changes
.png){kind=icon}
PRE
AI
DOI：10.1007/s10664-025-10763-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Code change representation plays a pivotal role in automating numerous software engineering tasks, such as classifying code change correctness or generating natural language summaries of code changes. Recent studies have leveraged deep learning to derive effective code change representation, primarily focusing on capturing changes in token sequences or Abstract Syntax Trees (ASTs). However, these current state-of-the-art representations do not explicitly calculate the intention semantic induced by the change on the AST, nor do they effectively explore the surrounding contextual information of the modified lines. To address this, we propose a new code change representation methodology, Patcherizer, which we refer to as our tool. This innovative approach explores the intention features of the context and structure, combining the context around the code change along with two novel representations. These new representations capture the sequence intention inside the code changes in the code change and the graph intention inside the structural changes of AST graphs before and after the code change. This comprehensive representation allows us to better capture the intentions underlying a code change. Patcherizer builds on graph convolutional neural networks for the structural input representation of the intention graph and on transformers for the intention sequence representation. We assess the generalizability of Patcherizer ’s learned embeddings on three tasks: (1) Generating code change description in NL, (2) Predicting code change correctness in program repair, and (3) Code change intention detection. Experimental results show that the learned code change representation is effective for all three tasks and achieves superior performance to the state-of-the-art (SOTA) approaches. For instance, on the popular task of code change description generation (a.k.a. commit message generation), Patcherizer achieves an average improvement of 19.39%, 8.71%, and 34.03% in terms of BLEU, ROUGE-L, and METEOR metrics, respectively.
Keywords:
Code change representation
Code change correctness
Message generation
Journal
IF:
3.6
Papers:
2.0K
Citations:
5.3K
Organization
View more organizations
Cited Papers
ShareSaveShareSaveAn Attention-Seq2Seq Model Based on CRNN Encoding for Automatic Labanotation Generation from Motion Capture Data.png)
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)IF0
PREAI
ShareSaveCoreGen: Contextualized Code Representation Learning for Commit Message GenerationNEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAIShareSaveShareSave View more