Skip to yearly menu bar Skip to main content


Poster

Learning to Infer Program Sketches

Maxwell Nye · Luke Hewitt · Josh Tenenbaum · Armando Solar-Lezama

Pacific Ballroom #182

Keywords: [ Other Applications ] [ Probabilistic Programming ] [ Structured Prediction ]


Abstract:

Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction. The key idea of this work is that a flexible combination of pattern recognition and explicit reasoning can be used to solve these complex programming problems. We propose a method for dynamically integrating these types of information. Our novel intermediate representation and training algorithm allow a program synthesis system to learn, without direct supervision, when to rely on pattern recognition and when to perform symbolic search. Our model matches the memorization and generalization performance of neural synthesis and symbolic search, respectively, and achieves state-of-the-art performance on a dataset of simple English description-to-code programming problems.

Live content is unavailable. Log in and register to view live content