PhD Dissertation Proposal by ZHANG Ting | Software Text Analysis with Pre-trained Language Models

Recent years have seen rapid growth in the field of software engineering (SE), with a vast number of software artifacts being created and shared. These artifacts include source code, bug reports, and pull requests etc.. Analyzing these artifacts is crucial for various automatic SE tasks, which is beneficial for boosting software development efficiency. However, analyzing software artifacts is challenging due to the unstructured and diverse nature of software text. To address this challenge, researchers have explored various approaches, including natural language processing techniques. With the advancement of pre-trained language models (PLMs) such as BERT and GPT, there is a growing interest in exploring their potential for software text analysis tasks.
 
This dissertation proposal aims to investigate the use of advanced PLMs to analyze different types of software-related texts, ranging from SE-specific artifacts like pull requests to general texts such as tweets. The main goal is to explore how these PLMs can be used for various software text analysis tasks, such as classification and generation.

ZHANG Ting, is a Ph.D. candidate at SMU SCIS, supervised by Prof. David Lo and Prof. Lingxiao Jiang. Her research focuses on automatic software bug management, from detecting duplicate bug reports to repairing API misuse bugs.