Standard
Learning to Represent Patches. / Tang, Xunzhu; Tian, Haoye; Chen, Zhenghan et al.
ICSE-Companion '24: Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings. New York: ACM, 2024. p. 396-397 (Proceedings - International Conference on Software Engineering).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Tang, X, Tian, H, Chen, Z, Pian, W
, Ezzini, S, Kabore, AK, Habib, A, Klein, J & Bissyande, TF 2024,
Learning to Represent Patches. in
ICSE-Companion '24: Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings. Proceedings - International Conference on Software Engineering, ACM, New York, pp. 396-397, 46th International Conference on Software Engineering: Companion, ICSE-Companion 2024, Lisbon, Portugal,
14/04/24.
https://doi.org/10.1145/3639478.3643521APA
Tang, X., Tian, H., Chen, Z., Pian, W.
, Ezzini, S., Kabore, A. K., Habib, A., Klein, J., & Bissyande, T. F. (2024).
Learning to Represent Patches. In
ICSE-Companion '24: Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings (pp. 396-397). (Proceedings - International Conference on Software Engineering). ACM.
https://doi.org/10.1145/3639478.3643521Vancouver
Tang X, Tian H, Chen Z, Pian W
, Ezzini S, Kabore AK et al.
Learning to Represent Patches. In ICSE-Companion '24: Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings. New York: ACM. 2024. p. 396-397. (Proceedings - International Conference on Software Engineering). Epub 2024 Apr 14. doi: 10.1145/3639478.3643521
Author
Tang, Xunzhu ; Tian, Haoye ; Chen, Zhenghan et al. /
Learning to Represent Patches. ICSE-Companion '24: Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings. New York : ACM, 2024. pp. 396-397 (Proceedings - International Conference on Software Engineering).
Bibtex
@inproceedings{ec3e25dd9f5646159c89484465a876c3,
title = "Learning to Represent Patches",
abstract = "We propose Patcherizer, a novel patch representation methodology that combines context and structure intention features to capture the semantic changes in Abstract Syntax Trees (ASTs) and surrounding context of code changes. Utilizing graph convolutional neural networks and transformers, Patcherizer effectively captures the underlying intentions of patches, outperforming state-of-the-art representations with significant improvements in BLEU, ROUGE-L, and METEOR metrics for generating patch descriptions.",
author = "Xunzhu Tang and Haoye Tian and Zhenghan Chen and Weiguo Pian and Saad Ezzini and Kabore, {Abdoul Kader} and Andrew Habib and Jacques Klein and Bissyande, {Tegawende F.}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE Computer Society. All rights reserved.; 46th International Conference on Software Engineering: Companion, ICSE-Companion 2024 ; Conference date: 14-04-2024 Through 20-04-2024",
year = "2024",
month = may,
day = "23",
doi = "10.1145/3639478.3643521",
language = "English",
series = "Proceedings - International Conference on Software Engineering",
publisher = "ACM",
pages = "396--397",
booktitle = "ICSE-Companion '24",
}
RIS
TY - GEN
T1 - Learning to Represent Patches
AU - Tang, Xunzhu
AU - Tian, Haoye
AU - Chen, Zhenghan
AU - Pian, Weiguo
AU - Ezzini, Saad
AU - Kabore, Abdoul Kader
AU - Habib, Andrew
AU - Klein, Jacques
AU - Bissyande, Tegawende F.
N1 - Publisher Copyright:
© 2024 IEEE Computer Society. All rights reserved.
PY - 2024/5/23
Y1 - 2024/5/23
N2 - We propose Patcherizer, a novel patch representation methodology that combines context and structure intention features to capture the semantic changes in Abstract Syntax Trees (ASTs) and surrounding context of code changes. Utilizing graph convolutional neural networks and transformers, Patcherizer effectively captures the underlying intentions of patches, outperforming state-of-the-art representations with significant improvements in BLEU, ROUGE-L, and METEOR metrics for generating patch descriptions.
AB - We propose Patcherizer, a novel patch representation methodology that combines context and structure intention features to capture the semantic changes in Abstract Syntax Trees (ASTs) and surrounding context of code changes. Utilizing graph convolutional neural networks and transformers, Patcherizer effectively captures the underlying intentions of patches, outperforming state-of-the-art representations with significant improvements in BLEU, ROUGE-L, and METEOR metrics for generating patch descriptions.
U2 - 10.1145/3639478.3643521
DO - 10.1145/3639478.3643521
M3 - Conference contribution/Paper
AN - SCOPUS:85194845232
T3 - Proceedings - International Conference on Software Engineering
SP - 396
EP - 397
BT - ICSE-Companion '24
PB - ACM
CY - New York
T2 - 46th International Conference on Software Engineering: Companion, ICSE-Companion 2024
Y2 - 14 April 2024 through 20 April 2024
ER -
