Year in School
REU Faculty Mentor
Research Area Interest
Dataset Augmentation for Better Semantical Learning
Biography & Research Abstract
The ultimate performance of the neural models for coding and code analysis tasks depends on two factors: (1) the quality of the training dataset and (2) the neural architecture. The focus of state-of-the-art has been on the latter factor, i.e., designing neural architectures and models that can learn the best from some projects in the dataset. These models, while have improved over time to incorporate semantic information such as control flow, data flow, and structured syntax, they have been shown to be vulnerable to adversarial attacks that slightly change the syntax of the code, but preserve the semantics. To advance the state of neural models for code, we aim to focus on the former factor, i.e., augment existing training datasets in such a way that models learn code semantics. The project involves augmenting the dataset of existing neural models for code, retraining them with the new dataset, and assessing the impact of additional data on the performance of these models.
My name is Eren Polat, I am a junior Computer Science student at Bilkent University. I am a graduate of METU High School. From a young age, I have been fascinated and interested in mathematics and I have decided to pursue that interest in computer science. I feel fortunate to study at Bilkent University where I had the chance to improve myself in both theoretical and practical ways. I've also had a research internship experience at University of Cambridge - Affective Computing Lab where I had the opportunity to grasp the fundamentals of ML, Computer Vision and gain experience in conducting research.