Problem Statement

current coding pre-training systems heavily rely on either an encoder-only model similar to BERT or a decoder-only model like GPT.

Either way, it is suboptimal for generation and understanding tasks.

CodeBERT needs an additional decoder when used for tasks like code summarization. Apart from the above issue, most current methods adopt the conventional NLP pre-training techniques on source code by considering it a sequence of tokens like in natural language.

This largely ignores the rich structural information present in programming languages, which is vital to comprehend its semantics fully.