Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples

Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani

Abstract:

Synthesizing user-intended programs from a small number of input-output exam-
ples is a challenging problem with several important applications like spreadsheet
manipulation, data wrangling and code refactoring. Existing synthesis systems
either completely rely on deductive logic techniques that are extensively hand-
engineered or on purely statistical models that need massive amounts of data, and in
general fail to provide real-time synthesis on challenging benchmarks. In this work,
we propose Neural Guided Deductive Search (NGDS), a hybrid synthesis technique
that combines the best of both symbolic logic techniques and statistical models.
Thus, it produces programs that satisfy the provided specifications by construction
and generalize well on unseen examples, similar to data-driven systems. Our
technique effectively utilizes the deductive search framework to reduce the learning
problem of the neural component to a simple supervised learning setup. Further,
this allows us to both train on sparingly available real-world data and still leverage
powerful recurrent neural network encoders. We demonstrate the effectiveness
of our method by evaluating on real-world customer scenarios by synthesizing
accurate programs with up to 12× speed-up compared to state-of-the-art systems.

TL;DR: We integrate symbolic (deductive) and statistical (neural-based) methods to enable real-time program synthesis with almost perfect generalization from 1 input-output example.

Keywords: Program synthesis, deductive search, deep learning, program induction, recurrent neural networks