Write a Blog >>

Recommender systems are a valuable tool for software engineers. For example, they can provide developers with a ranked list of files likely to contain a bug, or multiple auto-complete suggestions for a given method stub. However, the way these recommender systems interact with developers is often rudimentary—a long list of recommendations only ranked by the model’s confidence. In this vision paper, we lay out our research agenda for re-imagining how recommender systems for software engineering communicate their insights to developers. When issuing recommendations, we aim to recommend diverse rather than redundant solutions and present them in ways that highlight their differences. We also want to allow for seamless and interactive navigation of suggestions while striving for holistic end-to-end evaluations. By doing so, we believe that recommender systems can play an even more important role in helping developers write better software.

Christoph Treude is a Senior Lecturer in Software Engineering in the School of Computing and Information Systems at the University of Melbourne. The goal of his research is to improve the quality of software and the productivity of those producing it, with a particular focus on getting information to software developers when and where they need it.

His research combines empirical studies with the innovation of tools and approaches that take the wide variety of natural language artefacts in software repositories into account. He has authored more than 100 scientific articles with more than 200 co-authors, and his work has received an ARC Discovery Early Career Research Award (2018-2020), industry funding from Google, Facebook, and DST, as well as four best paper awards including two ACM SIGSOFT Distinguished Paper Awards. Prior to joining the University of Melbourne, Christoph Treude held a Senior Lecturer position at the University of Adelaide and worked as a postdoctoral researcher at McGill University, the University of São Paulo, and the Federal University of Rio Grande do Norte. He currently serves as a board member on the Editorial Board of the Empirical Software Engineering journal and was general co-chair for the 36th IEEE International Conference on Software Maintenance and Evolution.

Thu 13 Oct

Displayed time zone: Eastern Time (US & Canada) change

10:00 - 12:00
Technical Session 22 - Code Summarization and RecommendationResearch Papers / NIER Track / Journal-first Papers / Industry Showcase at Banquet A
Chair(s): Houari Sahraoui Université de Montréal
10:00
20m
Research paper
Identifying Solidity Smart Contract API Documentation Errors
Research Papers
Chenguang Zhu The University of Texas at Austin, Ye Liu Nanyang Technological University, Xiuheng Wu Nanyang Technological University, Singapore, Yi Li Nanyang Technological University
Pre-print
10:20
10m
Vision and Emerging Results
Few-shot training LLMs for project-specific code-summarization
NIER Track
Toufique Ahmed University of California at Davis, Prem Devanbu Department of Computer Science, University of California, Davis
DOI Pre-print
10:30
20m
Research paper
Answer Summarization for Technical Queries: Benchmark and New Approach
Research Papers
Chengran Yang Singapore Management University, Bowen Xu School of Information Systems, Singapore Management University, Ferdian Thung Singapore Management University, Yucen Shi Singapore Management University, Ting Zhang Singapore Management University, Zhou Yang Singapore Management University, Xin Zhou , Jieke Shi Singapore Management University, Junda He Singapore Management University, DongGyun Han Royal Holloway, University of London, David Lo Singapore Management University
10:50
20m
Paper
Code Structure Guided Transformer for Source Code SummarizationVirtual
Journal-first Papers
Shuzheng Gao Harbin Institute of Technology, Cuiyun Gao Harbin Institute of Technology, Yulan He University of Warwick, Jichuan Zeng The Chinese University of Hong Kong, Lun Yiu Nie Tsinghua University, Xin Xia Huawei Software Engineering Application Technology Lab, Michael Lyu The Chinese University of Hong Kong
11:10
10m
Vision and Emerging Results
Taming Multi-Output Recommenders for Software EngineeringVirtual
NIER Track
Christoph Treude University of Melbourne
11:20
20m
Industry talk
MV-HAN: A Hybrid Attentive Networks based Multi-View Learning Model for Large-scale Contents RecommendationVirtual
Industry Showcase
Ge Fan Tencent Inc., Chaoyun Zhang Tencent Inc., Kai Wang Tencent Inc., Junyang Chen Shenzhen University
DOI Pre-print
11:40
20m
Research paper
Which Exception Shall We Throw?Virtual
Research Papers
Hao Zhong Shanghai Jiao Tong University