A Syntactic Neural Model for General-Purpose Code Generation
This addresses the challenge of scalable and accurate code generation for developers, representing a strong incremental advance by integrating syntax into neural models.
The paper tackles the problem of generating general-purpose source code from natural language descriptions by proposing a neural architecture that incorporates a grammar model to capture target syntax, achieving state-of-the-art results that outperform previous methods.
We consider the problem of parsing natural language descriptions into source code written in a general-purpose programming language like Python. Existing data-driven methods treat this problem as a language generation task without considering the underlying syntax of the target programming language. Informed by previous work in semantic parsing, in this paper we propose a novel neural architecture powered by a grammar model to explicitly capture the target syntax as prior knowledge. Experiments find this an effective way to scale up to generation of complex programs from natural language descriptions, achieving state-of-the-art results that well outperform previous code generation and semantic parsing approaches.