mlsanityData to 7 Oct 2026

Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques

arXiv 2305.17378 ↗First posted 27 May 2023cs.CL cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs). In this study, we empirically investigate improving an LM's generalization in semantic parsing with two simple techniques: at the token level, we introduce a token preprocessing method to preserve the semantic boundaries of tokens produced by LM tokenizers; at the sequence level, we propose to use special tokens to mark the boundaries of components aligned between input and output. Our experimental results on two text-to-SQL semantic parsing datasets show that our token preprocessing, although simple, can substantially improve the LM performance on both types of generalization, and our component boundary marking method is particularly helpful for compositional generalization.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 27 May 2023.

Builds on

29 of 45 references.

References · 29

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  4. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  5. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  6. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  7. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  8. 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 280
  9. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  10. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  11. 2016Language to Logical Form with Neural Attentioncited by 158
  12. 2019Good-Enough Compositional Data Augmentationcited by 158
17 more
  1. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
  2. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136
  3. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  4. 2020Task-Oriented Dialogue as Dataflow Synthesiscited by 122
  5. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  6. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  7. 2020Span-based Semantic Parsing for Compositional Generalizationcited by 77
  8. 2018SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Taskcited by 74
  9. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
  10. 2020Learning to Recombine and Resample Data for Compositional Generalizationcited by 65
  11. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  12. 2021Meta-Learning to Compositionally Generalizecited by 62
  13. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  14. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  15. 2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
  16. 2021Structured Reordering for Modeling Latent Alignments in Sequence Transductioncited by 17
  17. 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 12; 2025: 7; 2026: 2.

23 papers.

Sort:

By area:

  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  2. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  3. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  4. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  5. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  6. 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoningcited by 49
  7. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 35
  8. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  9. 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 17
  10. 2024SQL-to-Schema Enhances Schema Linking in Text-to-SQLcited by 12
  11. 2023Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparisoncited by 6
  12. 2024Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systemscited by 6
11 more
  1. 2025Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequenciescited by 5
  2. 2024Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injectioncited by 2
  3. 2024Towards Agentic Schema Refinementcited by 2
  4. 2025Structural Deep Encoding for Table Question Answeringcited by 2
  5. 2025AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generationcited by 2
  6. 2024Understanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic Parsingcited by 1
  7. 2026ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarificationcited by 1
  8. 2025Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoningcited by 0
  9. 2025Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsingcited by 0
  10. 2025Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQLcited by 0
  11. 2026The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactionscited by 0