Multi-Task Program Error Repair and Explanatory Diagnosis
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913635714990080 |
|---|---|
| author | Xu, Zhenyu Sheng, Victor S. |
| author_facet | Xu, Zhenyu Sheng, Victor S. |
| contents | Program errors can occur in any type of programming, and can manifest in a variety of ways, such as unexpected output, crashes, or performance issues. And program error diagnosis can often be too abstract or technical for developers to understand, especially for beginners. The goal of this paper is to present a novel machine-learning approach for Multi-task Program Error Repair and Explanatory Diagnosis (mPRED). A pre-trained language model is used to encode the source code, and a downstream model is specifically designed to identify and repair errors. Programs and test cases will be augmented and optimized from several perspectives. Additionally, our approach incorporates a "chain of thoughts" method, which enables the models to produce intermediate reasoning explanations before providing the final correction. To aid in visualizing and analyzing the program structure, we use a graph neural network for program structure visualization. Overall, our approach offers a promising approach for repairing program errors across different programming languages and providing helpful explanations to programmers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07271 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Task Program Error Repair and Explanatory Diagnosis Xu, Zhenyu Sheng, Victor S. Software Engineering Artificial Intelligence Program errors can occur in any type of programming, and can manifest in a variety of ways, such as unexpected output, crashes, or performance issues. And program error diagnosis can often be too abstract or technical for developers to understand, especially for beginners. The goal of this paper is to present a novel machine-learning approach for Multi-task Program Error Repair and Explanatory Diagnosis (mPRED). A pre-trained language model is used to encode the source code, and a downstream model is specifically designed to identify and repair errors. Programs and test cases will be augmented and optimized from several perspectives. Additionally, our approach incorporates a "chain of thoughts" method, which enables the models to produce intermediate reasoning explanations before providing the final correction. To aid in visualizing and analyzing the program structure, we use a graph neural network for program structure visualization. Overall, our approach offers a promising approach for repairing program errors across different programming languages and providing helpful explanations to programmers. |
| title | Multi-Task Program Error Repair and Explanatory Diagnosis |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2410.07271 |