arxivst stuff from arxiv that you should probably bookmark

Deep API Programmer: Learning to Program with APIs

Abstract · Apr 14, 2017 02:04 ·

programs r3nn apis transformation dapip dsl regular lookup gulwani strings cs-ai cs-lg

Arxiv Abstract

  • Surya Bhupatiraju
  • Rishabh Singh
  • Abdel-rahman Mohamed
  • Pushmeet Kohli

We present DAPIP, a Programming-By-Example system that learns to program with APIs to perform data transformation tasks. We design a domain-specific language (DSL) that allows for arbitrary concatenations of API outputs and constant strings. The DSL consists of three family of APIs: regular expression-based APIs, lookup APIs, and transformation APIs. We then present a novel neural synthesis algorithm to search for programs in the DSL that are consistent with a given set of examples. The search algorithm uses recently introduced neural architectures to encode input-output examples and to model the program search in the DSL. We show that synthesis algorithm outperforms baseline methods for synthesizing programs on both synthetic and real-world benchmarks.

Read the paper (pdf) »