Retrieval-Based Neural Code Generation

Understand

In models to generate program source code from natural language, representing this code in a tree structure has been a common approach.

• However, existing methods often fail to generate complex code correctly due to a lack of ability to memorize large and complex structures.
• We introduce ReCode, a method based on subtree retrieval that makes it possible to explicitly reference existing code examples within a neural code generation model.
• First, we retrieve sentences that are similar to input sentences using a dynamic-programming-based sentence similarity scoring method.