Pseudocode Generation from Source Code Using the BART Model

In the software development process, more than one developer may work on developing the same program and bugs in the program may be fixed by a different developer; therefore, understanding the source code is an important issue. Pseudocode plays an important role in solving this problem, as it helps...

Full description

Saved in:
Bibliographic Details
Published in:Mathematics (Basel) 2022-11, Vol.10 (21), p.3967
Main Authors: Alokla, Anas, Gad, Walaa, Nazih, Waleed, Aref, Mustafa, Salem, Abdel-badeeh
Format: Article
Language:English
Subjects:
Autoregression (Statistics)
Autoregressive models
BART
BERT
Code generators
Datasets
Food science
GPT
Language
Machine translation
Mathematical research
Natural language
natural language processing
neural machine translation
Neural networks
Program generators
Pseudocode
pseudocode generation
Software
Software development
Source code
Technology application
Transformers
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the software development process, more than one developer may work on developing the same program and bugs in the program may be fixed by a different developer; therefore, understanding the source code is an important issue. Pseudocode plays an important role in solving this problem, as it helps the developer to understand the source code. Recently, transformer-based pre-trained models achieved remarkable results in machine translation, which is similar to pseudocode generation. In this paper, we propose a novel automatic pseudocode generation from the source code based on a pre-trained Bidirectional and Auto-Regressive Transformer (BART) model. We fine-tuned two pre-trained BART models (i.e., large and base) using a dataset containing source code and its equivalent pseudocode. In addition, two benchmark datasets (i.e., Django and SPoC) were used to evaluate the proposed model. The proposed model based on the BART large model outperforms other state-of-the-art models in terms of BLEU measurement by 15% and 27% for Django and SPoC datasets, respectively.
ISSN:2227-7390
2227-7390
DOI:10.3390/math10213967