I’m a third year Ph.D Candidate in Computer Science at School of Information Systems, Singapore Management University (SIS). I started my Ph.D at August, 2016. At SIS, I’m fortunate to be advised by Associate Prof. Lingxiao Jiang.
I obtained a Bachelor Degree in Advanced Program Computer Science, which is a honour program at Ho Chi Minh University of Science (HCMUS). At HCMUS, I did my undergraduate thesis under the supervision of Prof. Dinh Ba Tien.
My interests lie at the intersection of Software Mining, Natural Language Processing, and Machine Learning. I am interested in employing the power of Machine Learning to solve challenging software engineering problem.
Concretely, I’m focusing on answering the two fundamental questions:
- How to build a good representation learning model for programming language? Intuitively, Deep Learning alone is not enough to learn the rich structural and semantic features that hide inside the code. As such, my goal is to combine Deep Learning and Program Analysis to leverage the best of both that can lift up the performance of a specific software engineering task.
- How can we properly interpret the Deep Learning model for the programming language? Despite widespread adoption, Deep Learning (DL) models remain mostly black boxes. The problem is even more severe in the software engineering field, where most of the DL-based model is built based on some human heuristics with try and error. Understanding the reasons and able to interpret the predictions is quite important in assessing trust, which is fundamental if one plans to take action based on a prediction. I’m doing some studies to find the connection between the human and the DL-based model on how they understand the source code.
More details about the projects I am working on can be found here.
- Feb-2019: Our paper “Towards Zero Knowledge Learning for Cross Language API Mappings” has been accepted at ACM Student Research Competition Track (SRC), ICSE 2019, Montreal, Canada,.
- Nov-2018: Our paper “Bilateral Dependency Neural Networks for Cross-Language Algorithm Classification” has been accepted at Research Track, SANER 2019, Hangzhou, China.
- Feb-2018: Our paper “Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Code” has received the ACM SIGSOFT Distinguished Paper Award.
- Oct-2017: Our paper “Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Code” has been accepted at New Ideas and Emerging Technologies Results Track (NIER), ICSE 2018, Gothenburg, Sweden.