Towards demystifying dimensions of source code embeddings
Md Rafiqul Islam Rabin, Arjun Mukherjee, Omprakash Gnawali, Mohammad Amin Alipour · 2020
Source code representations are key in applying machine learning techniques for processing and analyzing programs. A popular approach in representing source code is neural source code embeddings that represents programs with high-dimensional vectors computed by training deep neural networks on a large volume of programs. Although successful, there is little known about the contents of these vectors and their characteristics.