mlsanityData to 13 Oct 2026

Learning to Describe Solutions for Bug Reports Based on Developer Discussions

arXiv 2110.04353 ↗First posted 8 Oct 2021cs.CL cs.SEcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 30 of its 58 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

30 of 58 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,106
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,884
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,893
  4. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,288
  5. 2015Pointer Networkscited by 884
  6. 2019Text Summarization with Pretrained Encoderscited by 554
  7. 2021Unified Pre-training for Program Understanding and Generationcited by 366
  8. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  9. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  10. 2017Learning to Represent Programs with Graphscited by 220
  11. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  12. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 179
18 more
  1. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  2. 2018Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflowcited by 165
  3. 2020A Transformer-based Approach for Source Code Summarizationcited by 132
  4. 2016A Convolutional Attention Network for Extreme Summarization of Source Codecited by 91
  5. 2018Structured Neural Summarizationcited by 54
  6. 2019Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Studycited by 40
  7. 2020Code and Named Entity Recognition in StackOverflowcited by 39
  8. 2019How Often Do Single-Statement Bugs Occur? The ManySStuBs4J Datasetcited by 36
  9. 2020Learning to Update Natural Language Comments Based on Code Changescited by 31
  10. 2018StaQC: A Systematically Mined Question-Code Dataset from Stack Overflowcited by 30
  11. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  12. 2017A Neural Architecture for Generating Natural Language Descriptions from Source Code Changescited by 23
  13. 2021Impact of Evaluation Methodologies on Code Summarizationcited by 11
  14. 2019Analysis and Detection of Information Types of Open Source Software Issue Discussionscited by 9
  15. 2019Associating Natural Language Comment and Source Code Entitiescited by 6
  16. 2018Detecting Speech Act Types in Developer Question/Answer Conversations During Bug Repaircited by 5
  17. 2019"Won't We Fix this Issue?" Qualitative Characterization and Automated Identification of Wontfix Issues on GitHubcited by 4
  18. 2020On the Relevance of Cross-project Learning with Nearest Neighbours for Commit Message Generationcited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2023Learning Deep Semantics for Test Completioncited by 31
  2. 2023Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editingcited by 9
  3. 2024Enhancing Automated Program Repair with Solution Designcited by 8
  4. 2022Using Developer Discussions to Guide Fixing Bugs in Softwarecited by 3
  5. 2026You Know What I Mean: A Benchmark for Agentic Conversational Reference Groundingcited by 0