Ain't Nobody Got Time For Coding: Structure-Aware Program Synthesis From Natural Language

Program synthesis from natural language (NL) is practical for humans and, once technically feasible, would significantly facilitate software development and revolutionize end-user programming. The proposed architecture relies exclusively on neural components, and is built upon a tree2tree autoencoder trained on abstract syntax trees, combined with a pretrained word embedding and a bidirectional multi-layer LSTM for NL processing. The decoder features a doubly-recurrent LSTM with a novel signal propagation scheme and soft attention mechanism. When applied to a large dataset of problems proposed in a previous study, SAPS performs on par with or better than the method proposed there, producing correct programs in over 90% of cases. In contrast to other methods, it does not involve any non-neural components to post-process the resulting programs, and uses a fixed-dimensional latent representation as the only link between the NL analyzer and source code generator. Program synthesis consists in automatic or semiautomatic (e.g., interactive) generation of programs (or other executable structures) from specifications. This task can be posed in several ways. It is most common to assume that specification has the form of input-output pairs (tests), in which case synthesis resembles learning from examples.