We introduce a novel approach to source code representation to be used in combination with neural networks. Such a representation is designed to permit the production of a continuous vector for each code statement. In particular, we present how the representation is produced in the case of Java source code. We test our representation for three tasks: code summarization, statement separation, and code search. We compare with the state-of-the-art non-autoregressive and end-to-end models for these tasks. We conclude that all tasks benefit from the proposed representation to boost their performance in terms of f1-score, accuracy, and MRR, respectively. Moreover, we show how models trained on code summarization and models trained on statement separation can be combined to address methods with tangled responsibilities. Meaning that these models can be used to detect code misconduct.
Fold2Vec: Towards a Statement Based Representation of Code for Code Comprehension / F. Bertolotti, W. Cazzola. - In: ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY. - ISSN 1049-331X. - 32:1(2023 Feb 13), pp. 6.1-6.31. [10.1145/3514232]
Fold2Vec: Towards a Statement Based Representation of Code for Code Comprehension
F. Bertolotti
Primo
;W. CazzolaUltimo
2023
Abstract
We introduce a novel approach to source code representation to be used in combination with neural networks. Such a representation is designed to permit the production of a continuous vector for each code statement. In particular, we present how the representation is produced in the case of Java source code. We test our representation for three tasks: code summarization, statement separation, and code search. We compare with the state-of-the-art non-autoregressive and end-to-end models for these tasks. We conclude that all tasks benefit from the proposed representation to boost their performance in terms of f1-score, accuracy, and MRR, respectively. Moreover, we show how models trained on code summarization and models trained on statement separation can be combined to address methods with tangled responsibilities. Meaning that these models can be used to detect code misconduct.File | Dimensione | Formato | |
---|---|---|---|
tosem22-published.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
1.52 MB
Formato
Adobe PDF
|
1.52 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.