mlsanityData to 14 Oct 2026

EzSQL: An SQL intermediate representation for improving SQL-to-text Generation

arXiv 2411.18923 ↗First posted 28 Nov 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The SQL-to-text generation task traditionally uses template base, Seq2Seq, tree-to-sequence, and graph-to-sequence models. Recent models take advantage of pre-trained generative language models for this task in the Seq2Seq framework. However, treating SQL as a sequence of inputs to the pre-trained models is not optimal. In this work, we put forward a new SQL intermediate representation called EzSQL to align SQL with the natural language text sequence. EzSQL simplifies the SQL queries and brings them closer to natural language text by modifying operators and keywords, which can usually be described in natural language. EzSQL also removes the need for set operators. Our proposed SQL-to-text generation model uses EzSQL as the input to a pre-trained generative language model for generating the text descriptions. We demonstrate that our model is an effective state-of-the-art method to generate text narrations from SQL queries on the WikiSQL and Spider datasets. We also show that by generating pretraining data using our SQL-to-text generation model, we can enhance the performance of Text-to-SQL parsers.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 28 Nov 2024.

Builds on

24 of 30 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  9. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  10. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  11. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  12. 2016Data Recombination for Neural Semantic Parsingcited by 111
12 more
  1. 2018TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generationcited by 88
  2. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  3. 2018SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Taskcited by 74
  4. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 68
  5. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  6. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  7. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  8. 2018Robust Text-to-SQL Generation with Execution-Guided Decodingcited by 52
  9. 2017Learning to Paraphrase for Question Answeringcited by 46
  10. 2021Learning to Synthesize Data for Semantic Parsingcited by 41
  11. 2021Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsingcited by 33
  12. 2018SQL-to-Text Generation with Graph-to-Sequence Modelcited by 31

Built on by

Not cited yet.