Neural Program Search: Solving Programming Tasks from Description and Examples

02/12/2018
by   Illia Polosukhin, et al.
0

We present a Neural Program Search, an algorithm to generate programs from natural language description and a small number of input/output examples. The algorithm combines methods from Deep Learning and Program Synthesis fields by designing rich domain-specific language (DSL) and defining efficient search algorithm guided by a Seq2Tree model on it. To evaluate the quality of the approach we also present a semi-synthetic dataset of descriptions with test examples and corresponding programs. We show that our algorithm significantly outperforms a sequence-to-sequence model with attention baseline.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/14/2017

Deep API Programmer: Learning to Program with APIs

We present DAPIP, a Programming-By-Example system that learns to program...
research
12/01/2020

Latent Programmer: Discrete Latent Codes for Program Synthesis

In many sequence learning tasks, such as program synthesis and document ...
research
02/10/2020

Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis

Implementing enterprise process automation often requires significant te...
research
09/01/2021

Learning compositional programs with arguments and sampling

One of the most challenging goals in designing intelligent systems is em...
research
03/14/2018

A Static Program Slicing Approach for Output Stream Objects in JEE Applications

In this paper, we propose a program slicing approach for the output stre...
research
04/05/2014

MTD(f), A Minimax Algorithm Faster Than NegaScout

MTD(f) is a new minimax search algorithm, simpler and more efficient tha...
research
12/27/2019

Synthetic Datasets for Neural Program Synthesis

The goal of program synthesis is to automatically generate programs in a...

Please sign up or login with your details

Forgot password? Click here to reset