Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases
Not on the map. Why?
Abstract (arXiv)
Large Language Models (LLMs) have spurred progress in text-to-SQL, the task of generating SQL queries from natural language questions based on a given database schema. Despite the declarative nature of SQL, it continues to be a complex programming language. In this paper, we investigate the potential of an alternative query language with simpler syntax and modular specification of complex queries. The purpose is to create a query language that can be learned more easily by modern neural semantic parsing architectures while also enabling non-programmers to better assess the validity of the query plans produced by an interactive query plan assistant. The proposed alternative query language is called Query Plan Language (QPL). It is designed to be modular and can be translated into a restricted form of SQL Common Table Expressions (CTEs). The aim of QPL is to make complex data retrieval accessible to non-programmers by allowing users to express their questions in natural language while also providing an easier-to-verify target language. The paper demonstrates how neural LLMs can benefit from QPL's modularity to generate complex query plans in a compositional manner. This involves a question decomposition strategy and a planning stage. We conduct experiments on a version of the Spider text-to-SQL dataset that has been converted to QPL. The hierarchical structure of QPL programs enables us to measure query complexity naturally. Based on this assessment, we identify the low accuracy of existing text-to-SQL systems on complex compositional queries. We present ways to address the challenge of complex queries in an iterative, user-controlled manner, using fine-tuned LLMs and a variety of prompting strategies in a compositional manner.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 22 Dec 2023.
Builds on
34 of 42 references.
References · 34
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
- 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
- 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
- 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 284
- 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
22 more
- 2016Language to Logical Form with Neural Attentioncited by 158
- 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
- 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
- 2020Break It Down: A Question Understanding Benchmarkcited by 131
- 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 119
- 2020Unsupervised Question Decomposition for Question Answeringcited by 118
- 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
- 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
- 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 77
- 2018SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Taskcited by 74
- 2019Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsingcited by 74
- 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 68
- 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
- 2021Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Datacited by 43
- 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
- 2021Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretablecited by 35
- 2023ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretationcited by 24
- 2023Divide and Prompt: Chain of Thought Prompting for Text-to-SQLcited by 20
- 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16
- 2021Weakly Supervised Text-to-SQL Parsing through Question Decompositioncited by 15
- 2022Interpretable AMR-Based Question Decomposition for Multi-hop Question Answeringcited by 12
- 2022Compositional Task-Oriented Parsing as Abstractive Question Answeringcited by 10
Built on by
Citing papers per year: 2026: 1.
1 paper.