https://github.com/ruiqi-zhong/TestSuiteEval
공식 코드Semantic Evaluation for Text-to-SQL with Distilled Test Suites
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Text-to-SQL is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.
<span style="color:grey; opacity: 0.6">( Image credit: SyntaxSQLNet )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Semantic Evaluation for Text-to-SQL with Distilled Test Suites
Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL
Confidence Estimation for Error Detection in Text-to-SQL Systems
Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
Improving Generalization in Semantic Parsing by Increasing Natural Language Variation
Sigma: A dataset for text-to-code semantic parsing with statistical analysis
EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records
How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings
SQL-o1: Automatic Text-to-SQL Program Synthesis via Self-Reward Heuristic Search
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA
ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback
SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling
Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task
TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation
Large Language Models are Good Multi-lingual Learners : When LLMs Meet Cross-lingual Prompts
Benchmarking and Improving Text-to-SQL Generation under Ambiguity
Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect
Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression
A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability
Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph
Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.