A5065291839- Software Engineering Research
- Software Testing and Debugging Techniques
- Software Engineering Techniques and Practices
- Software Reliability and Analysis Research
- Open Source Software Innovations
- Expert finding and Q&A systems
- Text and Document Classification Technologies
- Topic Modeling
- Natural Language Processing Techniques
- Speech Recognition and Synthesis
- Recommender Systems and Techniques
- Advanced Malware Detection Techniques
- Formal Methods in Verification
Polytechnique Montréal
2021-2024
Jack Miller Center
2022
Shahid Beheshti University
2017
Automatic program synthesis is a long-lasting dream in software engineering. Recently, promising Deep Learning (DL) based solution, called Copilot, has been proposed by OpenAI and Microsoft as an industrial product. Although some studies evaluate the correctness of Copilot solutions report its issues, more empirical evaluations are necessary to understand how developers can benefit from it effectively. In this paper, we study capabilities two different programming tasks: (i) generating (and...
Large Language Models (LLMs) for code have gained significant attention recently. They can generate in different programming languages based on provided prompts, fulfilling a long-lasting dream Software Engineering (SE), i.e., automatic generation. Similar to human-written code, LLM-generated is prone bugs, and these bugs not yet been thoroughly examined by the community. Given increasing adoption of LLM-based generation tools (e.g., GitHub Copilot) SE activities, it critical understand...
Accurate assessment of developer expertise is crucial for the assignment an individual to perform a task or, more generally, be involved in project that requires adequate level knowledge. Potential programmers can come from large pool. Therefore, automatic means provide such written programs would highly valuable context.
LLM-based assistants, such as GitHub Copilot and ChatGPT, have the potential to generate code that fulfills a programming task described in natural language description, referred prompt. The widespread accessibility of these assistants enables users with diverse backgrounds integrate it into software projects. However, studies show generated by LLMs is prone bugs may miss various corner cases specifications. Presenting buggy can impact their reliability trust assistants. Moreover,...
One of the critical phases in software development is testing. Testing helps with identifying potential bugs and reducing maintenance costs. The goal automated test generation tools to ease tests by suggesting efficient bug-revealing tests. Recently, researchers have leveraged Large Language Models (LLMs) code generate unit While coverage generated was usually assessed, literature has acknowledged that weakly correlated efficiency bug detection. To improve over this limitation, paper, we...
Accurate assessment of the domain expertise developers is important for assigning proper candidate to contribute a project or attend job role. Since potential can come from large pool, automated this desirable goal. While previous methods have had some success within single software project, developer's contributions across multiple projects more challenging. In paper, we employ doc2vec represent as embedding vectors. These vectors are derived different sources that contain evidence...