Neuro-Symbolic Program Synthesis
Emilio Parisotto, Abdel-rahman Mohamed, Rishabh Singh, Lihong Li,, Dengyong Zhou, Pushmeet Kohli

TL;DR
This paper introduces Neuro-Symbolic Program Synthesis, a novel approach combining neural modules to generate interpretable programs from input-output examples, overcoming limitations of previous neural program induction methods.
Contribution
It proposes a new neuro-symbolic framework with two neural modules for program synthesis that generalizes to unseen tasks and produces interpretable programs.
Findings
Effective in synthesizing regex-based string transformations
Generalizes to new, unseen tasks during testing
Produces interpretable, domain-specific programs
Abstract
Recent years have seen the proposal of a number of neural architectures for the problem of Program Induction. Given a set of input-output examples, these architectures are able to learn mappings that generalize to new test inputs. While achieving impressive results, these approaches have a number of important limitations: (a) they are computationally expensive and hard to train, (b) a model has to be trained for each task (program) separately, and (c) it is hard to interpret or verify the correctness of the learnt mapping (as it is defined by a neural network). In this paper, we propose a novel technique, Neuro-Symbolic Program Synthesis, to overcome the above-mentioned problems. Once trained, our approach can automatically construct computer programs in a domain-specific language that are consistent with a set of input-output examples provided at test time. Our method is based on two…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSoftware Testing and Debugging Techniques · Software Engineering Research · Oil and Gas Production Techniques
