Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding
Not on the map. Why?
Abstract (arXiv)
In addressing the task of converting natural language to SQL queries, there are several semantic and syntactic challenges. It becomes increasingly important to understand and remedy the points of failure as the performance of semantic parsing systems improve. We explore semantic parse correction with natural language feedback, proposing a new solution built on the success of autoregressive decoders in text-to-SQL tasks. By separating the semantic and syntactic difficulties of the task, we show that the accuracy of text-to-SQL parsers can be boosted by up to 26% with only one turn of correction with natural language. Additionally, we show that a T5-base model is capable of correcting the errors of a T5-large model in a zero-shot, cross-parser setting.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 33 references that are in the map. First posted on arXiv 31 May 2023.
Builds on
26 of 33 references.
References · 26
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
- 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
- 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
- 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
- 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
- 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
14 more
- 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
- 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
- 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
- 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
- 2018TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generationcited by 88
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
- 2016Latent Predictor Networks for Code Generationcited by 73
- 2020Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedbackcited by 44
- 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
- 2019Grammar-based Neural Text-to-SQL Generationcited by 23
- 2022STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsingcited by 19
- 2021Towards Transparent Interactive Semantic Parsing via Step-by-Step Correctioncited by 9
- 2019Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parserscited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.