Exploiting machine learning techniques for analyzing programs has attracted much
attention. One key problem is how to represent code fragments well for follow-up analysis …

Learning representation for source code is a foundation of many program analysis tasks. In
recent years, neural networks have already shown success in this area, but most existing …

Learning code representations has found many uses in software engineering, such as code
classification, code search, comment generation, and bug prediction, etc. Although …

Program semantics learning is the core and fundamental for various code intelligent tasks
eg, vulnerability detection, clone detection. A considerable amount of existing works …

Recently program learning techniques have been proposed to process source code based
on syntactical structures (eg, abstract syntax trees) and/or semantic information (eg …

Code generation maps a program description to executable source code in a programming
language. Existing approaches mainly rely on a recurrent neural network (RNN) as the …

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been
widely adopted on downstream tasks for source code understanding. However, compared to …

Source code summarization--creating natural language descriptions of source code
behavior--is a rapidly-growing research topic with applications to automatic documentation …

Learning distributed representation of source code requires modelling its syntax and
semantics. Recent state-of-the-art models leverage highly structured source code …

Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two
complementary representations of the same computer program. Traditionally, designers of …