pith. sign in

arxiv: 1811.06837 · v1 · pith:7FMOFOPWnew · submitted 2018-11-14 · 💻 cs.LG · cs.SE· stat.ML

A Grammar-Based Structural CNN Decoder for Code Generation

classification 💻 cs.LG cs.SEstat.ML
keywords codegenerationlanguagemodelprogramconvolutiondecodergrammar-based
0
0 comments X
read the original abstract

Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more tokens than a natural language sentence, and thus it may be inappropriate for RNN to capture such a long sequence. In this paper, we propose a grammar-based structural convolutional neural network (CNN) for code generation. Our model generates a program by predicting the grammar rules of the programming language; we design several CNN modules, including the tree-based convolution and pre-order convolution, whose information is further aggregated by dedicated attentive pooling layers. Experimental results on the HearthStone benchmark dataset show that our CNN code generator significantly outperforms the previous state-of-the-art method by 5 percentage points; additional experiments on several semantic parsing tasks demonstrate the robustness of our model. We also conduct in-depth ablation test to better understand each component of our model.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.