How to formulate specific how-to questions in software development?
Mingwei Liu, Xin Peng, Andrian Marcus, Christoph Treude, Jiazhan Xie, Huanjun Xu, Yanjun Yang
摘要
Developers often ask how-to questions using search engines, technical Q&A communities, and interactive Q&A systems to seek help for specific programming tasks. However, they often do not formulate the questions in a specific way, making it hard for the systems to return the best answers. We propose an approach (TaskKG4Q) that interactively helps developers formulate a programming related how-to question. TaskKG4Q is using a programming task knowledge graph (task KG in short) mined from Stack Overflow questions, which provides a hierarchical conceptual structure for tasks in terms of [actions], [objects], and [constraints]. An empirical evaluation of the intrinsic quality of the task KG revealed that 75.0% of the annotated questions in the task KG are correct. The comparison between TaskKG4Q and two baselines revealed that TaskKG4Q can help developers formulate more specific how-to questions. More so, an empirical study with novice programmers revealed that they write more effective questions for finding answers to their programming tasks on Stack Overflow.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
引用它的顶会 Paper4
- CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code GenerationMingwei Liu, Tianyong Yang, Yiling Lou, Xueying Du 等ASE 2023 · 被引用 31 次
- Self-Supervised Query Reformulation for Code SearchYuetian Mao, Chengcheng Wan, Yuze Jiang, Xiaodong GuFSE 2023 · 被引用 14 次
- Recommending Analogical APIs via Knowledge Graph EmbeddingMingwei Liu, Yanjun Yang, Yiling Lou, Xin Peng 等FSE 2023 · 被引用 8 次
- Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case StudyMingwei Liu, Zheng Pei, Yanlin Wang, Zihao Wang 等FSE 2026
相关 Paper
- Generating Concept based API Element Comparison Using a Knowledge GraphYang Liu, Mingwei Liu, Xin Peng, Christoph Treude 等ASE 2020 · 被引用 28 次
- KG4CraSolver: Recommending Crash Solutions via Knowledge GraphXueying Du, Yiling Lou, Mingwei Liu, Xin Peng 等FSE 2023 · 被引用 3 次
- Automated Query Reformulation for Efficient Search based on Query Logs From Stack OverflowKaibo Cao, Chunyang Chen, Sebastian Baltes, Christoph Treude 等ICSE 2021 · 被引用 63 次
- Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient ModelingHussein Abdallah, Waleed Afandi, Panos Kalnis, Essam MansourICDE 2024 · 被引用 3 次
- On the Helpfulness of Answering Developer Questions on Discord with Similar Conversations and Posts from the PastAlexander Lill, André N. Meyer, Thomas FritzICSE 2024 · 被引用 5 次
