Multi-Task Program Error Repair and Explanatory Diagnosis

TL;DR

This paper introduces mPRED, a multi-task machine learning framework that repairs program errors and provides explanatory diagnosis using code encoding, error repair models, reasoning chains, and program structure visualization.

Contribution

It presents a novel multi-task approach combining error repair and explanation generation with graph neural networks and reasoning chains for improved program debugging.

Findings

Effective error repair across multiple programming languages

Enhanced explanations through chain of thoughts methodology

Improved program structure visualization for debugging

Abstract

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.