Structural Language Models of Code
This addresses the challenge of flexible code generation for developers, offering a novel method that can handle arbitrary code in any programming language, though it builds on prior structured approaches.
The paper tackles the problem of any-code completion, generating missing source code without restrictions on vocabulary or structure, by introducing structural language modeling (SLM) that models code as trees and significantly outperforms existing methods like seq2seq and structured approaches in generating Java and C# code.
We address the problem of any-code completion - generating a missing piece of source code in a given program without any restriction on the vocabulary or structure. We introduce a new approach to any-code completion that leverages the strict syntax of programming languages to model a code snippet as a tree - structural language modeling (SLM). SLM estimates the probability of the program's abstract syntax tree (AST) by decomposing it into a product of conditional probabilities over its nodes. We present a neural model that computes these conditional probabilities by considering all AST paths leading to a target node. Unlike previous techniques that have severely restricted the kinds of expressions that can be generated in this task, our approach can generate arbitrary code in any programming language. Our model significantly outperforms both seq2seq and a variety of structured approaches in generating Java and C# code. Our code, data, and trained models are available at http://github.com/tech-srl/slm-code-generation/ . An online demo is available at http://AnyCodeGen.org .