Learning Programmatic Idioms for Scalable Semantic Parsing

  title={Learning Programmatic Idioms for Scalable Semantic Parsing},
  author={Srini Iyer and A. Cheung and Luke Zettlemoyer},
  • Srini Iyer, A. Cheung, Luke Zettlemoyer
  • Published 2019
  • Computer Science
  • ArXiv
  • Programmers typically organize executable source code using high-level coding patterns or idiomatic structures such as nested loops, exception handlers and recursive blocks, rather than as individual code tokens. In contrast, state of the art (SOTA) semantic parsers still map natural language instructions to source code by building the code syntax tree one node at a time. In this paper, we introduce an iterative method to extract code idioms from large source code corpora by repeatedly… CONTINUE READING
    A Survey on Semantic Parsing
    • 20
    • PDF
    Program Synthesis and Semantic Parsing with Learned Code Idioms
    • 11
    • PDF
    Structural Language Models of Code.
    • 8
    • PDF
    Structural Language Models for Any-Code Generation
    • 6
    Semantic Scaffolds for Pseudocode-to-Code Generation
    • 2
    • PDF


    Publications referenced by this paper.
    Adam: A Method for Stochastic Optimization
    • 49,659
    • PDF
    Neural Machine Translation of Rare Words with Subword Units
    • 2,708
    • Highly Influential
    • PDF
    Bleu: a Method for Automatic Evaluation of Machine Translation
    • 12,026
    • PDF
    Abstract Syntax Networks for Code Generation and Semantic Parsing
    • 166
    • PDF
    Language to Logical Form with Neural Attention
    • 381
    • Highly Influential
    • PDF
    Mining idioms from source code
    • 109
    • Highly Influential
    • PDF
    Lexical Generalization in CCG Grammar Induction for Semantic Parsing
    • 192
    • PDF
    Latent Predictor Networks for Code Generation
    • 194
    • Highly Influential
    • PDF