Hello! I’m Luke Dramko, a PhD student and National Science Foundation Graduate Research Fellow. I am fortunate to be co-advised by Claire Le Goues and Bogdan Vasilescu, and I have the pleasure of collaborating with Graham Neubig and the CMU SEI.
I am interested in machine learning for natural language processing, with a current emphasis on learning source code. My present work is focused on applying this to reverse engineering for threat analysis in computer security. Currently, this kind of reverse engineering is a very time-intensive process for humans because the artifacts analyzed are often missing the very details that make software interpretable by humans. I'm collaborating with the CMU SEI to help make reverse engineering smoother and faster by using natural language processing techniques to infer those missing details.
While interning at GitHub, I built a scalable content-based repository recommendation system to serve all worldwide users. Watch my upcoming talk about my recommendation system work at GitHub Universe 2022.
I graduated Summa Cum Laude with a 4.0 GPA and bachelors degrees in Mathematics and Computer Science from the University of North Dakota.
- Dramko, L., Lacomis, J., Yin, P., Schwartz, E. J., Allamanis, M., Neubig, G., ... & Le Goues, C. (2022). DIRE and its Data: Neural Decompiled Variable Renamings with Respect to Software Class. ACM Transactions on Software Engineering and Methodology.
- Dokoohaki, H., Morrison, B. D., Raiho, A., Serbin, S. P., Zarada, K., Dramko, L., & Dietze, M. (2022). Development of an open-source regional data assimilation system in PEcAn v. 1.7. 2: application to carbon cycle reanalysis across the contiguous US using SIPNET. Geoscientific Model Development, 15(8), 3233-3252.
I recieved the National Science Foundation Graduate Research Fellowship (NSF GRF) in 2022.