Neural Programming by Example
This work addresses the challenge of automating program synthesis for string manipulation tasks, which is incremental as it applies existing neural network techniques to a known problem in programming by example.
The authors tackled the problem of automatically inferring computer programs from input-output examples, specifically for string manipulation tasks, by proposing a deep neural network model called Neural Programming by Example (NPBE). The results show that NPBE can effectively induce string manipulation programs, as demonstrated on common problems in spreadsheet systems.
Programming by Example (PBE) targets at automatically inferring a computer program for accomplishing a certain task from sample input and output. In this paper, we propose a deep neural networks (DNN) based PBE model called Neural Programming by Example (NPBE), which can learn from input-output strings and induce programs that solve the string manipulation problems. Our NPBE model has four neural network based components: a string encoder, an input-output analyzer, a program generator, and a symbol selector. We demonstrate the effectiveness of NPBE by training it end-to-end to solve some common string manipulation problems in spreadsheet systems. The results show that our model can induce string manipulation programs effectively. Our work is one step towards teaching DNN to generate computer programs.