# Neural Programming by Example

## TL;DR

This paper introduces NPBE, a deep neural network model that learns to generate string manipulation programs from input-output examples, advancing automated program synthesis in spreadsheet tasks.

## Contribution

The paper presents a novel neural network architecture for program induction from examples, specifically targeting string manipulation tasks in spreadsheets.

## Key findings

- NPBE effectively induces string manipulation programs
- The model demonstrates strong performance on spreadsheet string tasks
- End-to-end training shows promising results in program synthesis

## Abstract

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.