Robust Text-to-SQL Generation with Execution-Guided Decoding
We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty programs during the decoding procedure by conditioning on the execution of partially generated program. The mechanism can be used with any autoregressive generative model, which we demonstrate on four state-of-the-art recurrent or template-based semantic parsing models. We demonstrate that execution guidance universally improves model performance on various text-to-SQL datasets with different scales and query complexity: WikiSQL, ATIS, and GeoQuery. As a result, we achieve new state-of-the-art execution accuracy of 83.8% on WikiSQL.
Code (1)
Tasks
Semantic ParsingText to SQLText-To-SQLSimilar Papers 제목 키워드 기반
Improving Text-to-SQL with Schema Dependency Learning
Text-to-SQL aims to map natural language questions to SQL queries. The sketch-based method combined with execution-guided (EG) decoding strategy has shown a strong performance on the WikiSQL benchmark. However, execution…
Text to SQLText-To-SQLSeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising
In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture. In this paper, we present a simple yet effective approach that adapts transformer-based seq-to-seq mo…
DecoderDenoisingslot-fillingSlot Filling+2ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL
In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc sig…
Text to SQLText-To-SQLTreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation
Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, th…
Prompt EngineeringCode GenerationMonte Carlo Tree Search for Execution-Guided Program Repair with Large Language Models
Automated program repair with large language models remains challenging at the repository level due to long-horizon reasoning requirements and the limitations of autoregressive decoding. We present CodePilot, a hybrid fr…
Program Repair