Leveraging constraint logic programming for neural guided program synthesis

Lisa Zhang; Gregory Rosenblatt; Ethan Fetaya; Renjie Liao; William E. Byrd; Raquel Urtasun; Richard Zemel

Leveraging constraint logic programming for neural guided program synthesis

Lisa Zhang, Gregory Rosenblatt, Ethan Fetaya, Renjie Liao, William E. Byrd, Raquel Urtasun, Richard Zemel

Research output: Contribution to conference › Paper › peer-review

Abstract

We present a method for solving Programming by Example (PBE) problems that tightly integrates a neural network with a constraint logic programming system called miniKanren. Internally, miniKanren searches for a program that satisfies the recursive constraints imposed by the provided examples. Our Recurrent Neural Network (RNN) model uses these constraints as input to score candidate programs. We show evidence that using our method to guide miniKanren’s search is a promising approach to solving PBE problems.

Original language	English
State	Published - 2018
Externally published	Yes
Event	6th International Conference on Learning Representations, ICLR 2018 - Vancouver, Canada Duration: 30 Apr 2018 → 3 May 2018

Conference

Conference	6th International Conference on Learning Representations, ICLR 2018
Country/Territory	Canada
City	Vancouver
Period	30/04/18 → 3/05/18

All Science Journal Classification (ASJC) codes

Education
Computer Science Applications
Linguistics and Language
Language and Linguistics

Cite this

@conference{2a62375b5540438ab8ce1b997a158d32,

title = "Leveraging constraint logic programming for neural guided program synthesis",

abstract = "We present a method for solving Programming by Example (PBE) problems that tightly integrates a neural network with a constraint logic programming system called miniKanren. Internally, miniKanren searches for a program that satisfies the recursive constraints imposed by the provided examples. Our Recurrent Neural Network (RNN) model uses these constraints as input to score candidate programs. We show evidence that using our method to guide miniKanren{\textquoteright}s search is a promising approach to solving PBE problems.",

author = "Lisa Zhang and Gregory Rosenblatt and Ethan Fetaya and Renjie Liao and Byrd, {William E.} and Raquel Urtasun and Richard Zemel",

note = "Publisher Copyright: {\textcopyright} 6th International Conference on Learning Representations, ICLR 2018 - Workshop Track Proceedings. All rights reserved.; 6th International Conference on Learning Representations, ICLR 2018 ; Conference date: 30-04-2018 Through 03-05-2018",

year = "2018",

language = "الإنجليزيّة",

}

TY - CONF

T1 - Leveraging constraint logic programming for neural guided program synthesis

AU - Zhang, Lisa

AU - Rosenblatt, Gregory

AU - Fetaya, Ethan

AU - Liao, Renjie

AU - Byrd, William E.

AU - Urtasun, Raquel

AU - Zemel, Richard

PY - 2018

Y1 - 2018

N2 - We present a method for solving Programming by Example (PBE) problems that tightly integrates a neural network with a constraint logic programming system called miniKanren. Internally, miniKanren searches for a program that satisfies the recursive constraints imposed by the provided examples. Our Recurrent Neural Network (RNN) model uses these constraints as input to score candidate programs. We show evidence that using our method to guide miniKanren’s search is a promising approach to solving PBE problems.

AB - We present a method for solving Programming by Example (PBE) problems that tightly integrates a neural network with a constraint logic programming system called miniKanren. Internally, miniKanren searches for a program that satisfies the recursive constraints imposed by the provided examples. Our Recurrent Neural Network (RNN) model uses these constraints as input to score candidate programs. We show evidence that using our method to guide miniKanren’s search is a promising approach to solving PBE problems.

UR - http://www.scopus.com/inward/record.url?scp=85083951719&partnerID=8YFLogxK

M3 - محاضرة

T2 - 6th International Conference on Learning Representations, ICLR 2018

Y2 - 30 April 2018 through 3 May 2018

ER -

Leveraging constraint logic programming for neural guided program synthesis

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this