Learning to Describe Solutions for Bug Reports Based on Developer Discussions

TL;DR

This paper introduces a method to generate concise descriptions of bug solutions from developer discussions, combining natural language and source code, to speed up bug resolution.

Contribution

It presents a novel approach to synthesize bug solution descriptions from discussions using noisy supervision and real-time classification, establishing new benchmarks.

Findings

Effective in generating concise bug solution descriptions

Suitable for complex reasoning in bimodal dialogue contexts

Establishes new benchmarks for the task

Abstract

When a software bug is reported, developers engage in a discussion to collaboratively resolve it. While the solution is likely formulated within the discussion, it is often buried in a large amount of text, making it difficult to comprehend and delaying its implementation. To expedite bug resolution, we propose generating a concise natural language description of the solution by synthesizing relevant content within the discussion, which encompasses both natural language and source code. We build a corpus for this task using a novel technique for obtaining noisy supervision from repository changes linked to bug reports, with which we establish benchmarks. We also design two systems for generating a description during an ongoing discussion by classifying when sufficient context for performing the task emerges in real-time. With automated and human evaluation, we find this task to form an ideal testbed for complex reasoning in long, bimodal dialogue context.