Write a Blog >>
ICSE 2023
Sun 14 - Sat 20 May 2023 Melbourne, Australia
Fri 19 May 2023 14:30 - 14:45 at Meeting Room 104 - Software development tools Chair(s): Xing Hu

Code search aims to retrieve semantically relevant code snippets for a given natural language query. Recently, many approaches employing contrastive learning have shown promising results on code representation learning and greatly improved the performance of code search. However, there is still a lot of room for improvement in using contrastive learning for code search. In this paper, we propose CoCoSoDa to effectively utilize contrastive learning for code search via two key factors in contrastive learning: data augmentation and negative samples. Specifically, soft data augmentation is to dynamically masking or replacing some tokens with their types for input sequences to generate positive samples. Momentum mechanism is used to generate large and consistent representations of negative samples in a mini-batch through maintaining a queue and a momentum encoder. In addition, multimodal contrastive learning is used to pull together representations of code-query pairs and push apart the unpaired code snippets and queries. We conduct extensive experiments to evaluate the effectiveness of our approach on a large-scale dataset with six programming languages. Experimental results show that: (1) CoCoSoDa outperforms 18 baselines and especially exceeds CodeBERT, GraphCodeBERT, and UniXcoder by 13.3%, 10.5%, and 5.9% on average MRR scores, respectively. (2) The ablation studies show the effectiveness of each component of our approach. (3) We adapt our techniques to several different pre-trained models such as RoBERTa, CodeBERT, and GraphCodeBERT and observe a significant boost in their performance in code search. (4) Our model performs robustly under different hyper-parameters. Furthermore, we perform qualitative and quantitative analyses to explore reasons behind the good performance of our model.

Fri 19 May

Displayed time zone: Hobart change

13:45 - 15:15
13:45
15m
Talk
Safe low-level code without overhead is practical
Technical Track
Pre-print
14:00
15m
Talk
Sibyl: Improving Software Engineering Tools with SMT SelectionDistinguished Paper Award
Technical Track
Will Leeson University of Virgina, Matthew B Dwyer University of Virginia, Antonio Filieri AWS and Imperial College London
Pre-print
14:15
15m
Talk
Make Your Tools Sparkle with Trust: The PICSE Framework for Trust in Software Tools
SEIP - Software Engineering in Practice
Brittany Johnson George Mason University, Christian Bird Microsoft Research, Denae Ford Microsoft Research, Nicole Forsgren Microsoft Research, Thomas Zimmermann Microsoft Research
Pre-print
14:30
15m
Talk
CoCoSoDa: Effective Contrastive Learning for Code Search
Technical Track
Ensheng Shi Xi'an Jiaotong University, Wenchao Gu The Chinese University of Hong Kong, Yanlin Wang School of Software Engineering, Sun Yat-sen University, Lun Du Microsoft Research Asia, Hongyu Zhang The University of Newcastle, Shi Han Microsoft Research, Dongmei Zhang Microsoft Research, Hongbin Sun Xi'an Jiaotong University
Pre-print
14:45
7m
Talk
Task Context: A Tool for Predicting Code Context Models for Software Development Tasks
DEMO - Demonstrations
Yifeng Wang Zhejiang University, Yuhang Lin Zhejiang University, Zhiyuan Wan Zhejiang University, Xiaohu Yang Zhejiang University
Pre-print Media Attached
14:52
7m
Talk
Continuously Accelerating Research
NIER - New Ideas and Emerging Results
Sergey Mechtaev University College London, Jonathan Bell Northeastern University, Christopher Steven Timperley Carnegie Mellon University, Earl T. Barr University College London, Michael Hilton Carnegie Mellon University
Pre-print
15:00
7m
Talk
An Alternative to Cells for Selective Execution of Data Science Pipelines
NIER - New Ideas and Emerging Results
Lars Reimann University of Bonn, Günter Kniesel-Wünsche University of Bonn
Pre-print
15:07
7m
Talk
pytest-inline: An Inline Testing Tool for Python
DEMO - Demonstrations
Yu Liu University of Texas at Austin, Zachary Thurston Cornell University, Alan Han Cornell University, Pengyu Nie University of Texas at Austin, Milos Gligoric University of Texas at Austin, Owolabi Legunsen Cornell University