Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Neural Program Search: Solving Programming Tasks from Description and Examples
Illia Polosukhin, Alexander Skidanov
Feb 12, 2018 (modified: Feb 15, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract: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.
TL;DR:Program synthesis from natural language description and input / output examples via Tree-Beam Search over Seq2Tree model
Keywords:Deep learning, Structured Prediction, Natural Language Processing, Neural Program Synthesis
Enter your feedback below and we'll get back to you as soon as possible.