Neural Program Search: Solving Programming Tasks from Description and Examples
arXiv:1802.04335
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.
arXiv comment9 pages, 3 figures, ICLR workshop
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- DeepCoder: Learning to Write Programs
- Neural Programmer-Interpreters
- Neural GPUs Learn Algorithms
- Language to Logical Form with Neural Attention
- Latent Predictor Networks for Code Generation
- TerpreT: A Probabilistic Programming Language for Program Induction
- Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
- Deep API Programmer: Learning to Program with APIs
- WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia
Cited by in corpus (10)
- CODIT: Code Editing with Tree-Based Neural Models
- ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
- Hierarchical Poset Decoding for Compositional Generalization in Language
- NAPS: Natural Program Synthesis Dataset
- Program Synthesis with Pragmatic Communication
- Ain't Nobody Got Time For Coding: Structure-Aware Program Synthesis From Natural Language
- Comparison of Syntactic and Semantic Representations of Programs in Neural Embeddings
- Middle-Out Decoding
- On Adversarial Robustness of Synthetic Code Generation
- Type-driven Neural Programming by Example