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.

PDF, Arxiv

In Findings of the Annual Meeting of the Association for Computational Linguistics (ACL), May 2022.

@inproceedings{panthaplackel:acl2022, title={Learning to Describe Solutions for Bug Reports Based on Developer Discussions}, author={Sheena Panthaplackel and Junyi Jessy Li and Milos Gligoric and Raymond J. Mooney}, booktitle={Findings of the Annual Meeting of the Association for Computational Linguistics (ACL)}, month={May}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127949", year={2022} }

Slides (PDF) Poster Video