Výsledky vyhledávání - "Wang, Juhong"

Report

Deep Code Search with Naming-Agnostic Contrastive Multi-View Learning

Autor: Feng, Jiadong, Li, Wei, Wei, Zhao, Xu, Yong, Wang, Juhong, Li, Hui

Software development is a repetitive task, as developers usually reuse or get inspiration from existing implementations. Code search, which refers to the retrieval of relevant code snippets from a codebase according to the developer's intent that has

Externí odkaz: http://arxiv.org/abs/2408.09345

Zobrazit plný text záznamu

Report

On the Effectiveness of Large Language Models in Domain-Specific Code Generation

Autor: Lin, Yalan, Chen, Meng, Hu, Yuhan, Zhang, Hongyu, Wan, Chengcheng, Wei, Zhao, Xu, Yong, Wang, Juhong, Gu, Xiaodong

Large language models (LLMs) such as ChatGPT have shown remarkable capabilities in code generation. Despite significant achievements, they rely on enormous training data to acquire a broad spectrum of open-domain knowledge. Besides, their evaluation

Externí odkaz: http://arxiv.org/abs/2312.01639

Zobrazit plný text záznamu

Report

Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance

Autor: Zhang, Sheng, Li, Hui, Wang, Yanlin, Wei, Zhao, Xiu, Yong, Wang, Juhong, Ji, Rongong

Code search engine is an essential tool in software development. Many code search methods have sprung up, focusing on the overall ranking performance of code search. In this paper, we study code search from another perspective by analyzing the bias o

Externí odkaz: http://arxiv.org/abs/2311.14901

Zobrazit plný text záznamu

Report

EALink: An Efficient and Accurate Pre-trained Framework for Issue-Commit Link Recovery

Autor: Zhang, Chenyuan, Wang, Yanlin, Wei, Zhao, Xu, Yong, Wang, Juhong, Li, Hui, Ji, Rongrong

Publikováno v: IEEE/ACM International Conference on Automated Software Engineering,2023

Issue-commit links, as a type of software traceability links, play a vital role in various software development and maintenance tasks. However, they are typically deficient, as developers often forget or fail to create tags when making commits. Exist

Externí odkaz: http://arxiv.org/abs/2308.10759

Zobrazit plný text záznamu

Report

RefBERT: A Two-Stage Pre-trained Framework for Automatic Rename Refactoring

Autor: Liu, Hao, Wang, Yanlin, Wei, Zhao, Xu, Yong, Wang, Juhong, Li, Hui, Ji, Rongrong

Refactoring is an indispensable practice of improving the quality and maintainability of source code in software evolution. Rename refactoring is the most frequently performed refactoring that suggests a new name for an identifier to enhance readabil

Externí odkaz: http://arxiv.org/abs/2305.17708

Zobrazit plný text záznamu