Corpus ID: 53289148

Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters

  title={Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters},
  author={D. Lukovnikov and Nilesh Chakraborty and Jens Lehmann and Asja Fischer},
  • D. Lukovnikov, Nilesh Chakraborty, +1 author Asja Fischer
  • Published 2018
  • Computer Science
  • ArXiv
  • Translating natural language to SQL queries for table-based question answering is a challenging problem and has received significant attention from the research community. In this work, we extend a pointer-generator and investigate the order-matters problem in semantic parsing for SQL. Even though our model is a straightforward extension of a general-purpose pointer-generator, it outperforms early works for WikiSQL and remains competitive to concurrently introduced, more complex models… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Text-to-SQL Generation for Question Answering on Electronic Medical Records
    • 1
    • PDF


    Publications referenced by this paper.
    Semantic Parsing on Freebase from Question-Answer Pairs
    • 956
    • PDF
    Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
    • 300
    • Highly Influential
    Compositional Semantic Parsing on Semi-Structured Tables
    • 251
    • Highly Influential
    • PDF
    Semantic Parsing with Syntax- and Table-Aware SQL Generation
    • 34
    • PDF
    Neural Machine Translation by Jointly Learning to Align and Translate
    • 12,929
    • Highly Influential
    • PDF
    Robust Text-to-SQL Generation with Execution-Guided Decoding
    • 25
    • Highly Influential
    • PDF
    TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation
    • 90
    • Highly Influential
    • PDF
    Search-based Neural Structured Learning for Sequential Question Answering
    • 86
    • PDF
    Glove: Global Vectors for Word Representation
    • 14,712
    • Highly Influential
    • PDF
    Online Learning of Relaxed CCG Grammars for Parsing to Logical Form
    • 395
    • PDF