Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences

Abstract:

Code completion is an essential feature of IDEs, yet current autocompleters are restricted to either grammar-based or NLP-based single token completions. Both approaches have significant drawbacks: grammar-based autocompletion is very restricted in dynamically-typed language scenarios, whereas NLP-based autocompletion struggles to understand the semantics of the programming language, giving suggestions that ignore a developer’s context. In this work, we present CodeFill, a language model for autocompletion that combines structure and naming information.