PhD Dissertation Defense by BUI Duy Quoc Nghi | Novel Deep Learning Methods Combined with Static Analysis for Source Code Processing

Machine learning is one of the techniques that have been utilized to mine knowledge from existing software artifacts as a stage forward to understand the software's behaviors. The mined knowledge can be utilized for understanding big systems, reducing software maintenance costs, recognizing bugs, code refactoring, and so forth. On the other hand, with the help of program analysis techniques that enrich the representation of source code, it is a common belief that adding semantic descriptions (e.g., via code comments, visualizing code control flow graphs, etc.) enhances human understanding of programs. It is desirable to combine machine learning and program analysis so that one can leverage the best of both to increase the performance of software analytics. On one side, machine learning can analyze the source code of thousands of well-written software projects that can uncover patterns that partially characterize software that is reliable, easy to read, and easy to maintain. On the other side, the program analysis can be used to define rigorous and unique rules that are only available in programming languages, which enrich the representation of source code and help the machine learning to capture the patterns better.

In this dissertation, I will present novel source code modeling approaches to model the source code better and demonstrate the usefulness of such approaches in various software engineering tasks. The methods developed for the aims to utilize the advantages of both deep learning techniques and static code analysis techniques.

Bui Duy Quoc Nghi is a Ph.D. candidate in the School of Information Systems, Singapore Management University, advised by Associate Professor Lingxiao Jiang. His research focuses on building smart software engineering tools by combining machine learning and program analysis.