https://github.com/tomerwolgithub/question-decomposition-to-sql
공식 코드Weakly Supervised Text-to-SQL Parsing through Question Decomposition
Papers with Code 아카이브
Text-To-SQL
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 86
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/trais-lab/llm-structured-data
공식 코드Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
https://github.com/tshu-w/dbcopilot
공식 코드DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
https://github.com/uiuc-kang-lab/elt-bench
공식 코드ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines
https://github.com/venzino-han/probgate_ehrsql
공식 코드https://github.com/wangpinggl/TREQS
공식 코드Text-to-SQL Generation for Question Answering on Electronic Medical Records
https://github.com/wbbeyourself/dte
공식 코드Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
https://github.com/wbbeyourself/mac-sql
공식 코드MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
https://github.com/wbsg-uni-mannheim/selfrefinement4extractgpt
공식 코드Automated Self-Refinement and Self-Correction for LLM-based Product Attribute Value Extraction
https://github.com/wotchin/AnDB
공식 코드AnDB: Breaking Boundaries with an AI-Native Database for Universal Semantic Analysis
https://github.com/x-lance/medical-dataset
공식 코드CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset
https://github.com/x-lance/text2sql-gpt
공식 코드ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought
https://github.com/x-lance/text2sql-multiturn-gpt
공식 코드CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions
https://github.com/xgenerationlab/xiyan-dbdescgen
공식 코드https://github.com/yandex-research/sparqling-queries
공식 코드SPARQLing Database Queries from Intermediate Question Decompositions
https://github.com/yasufumy/spider-schema-linking-dataset
공식 코드An Investigation Between Schema Linking and Text-to-SQL Performance
https://github.com/ygan/natsql
공식 코드Natural SQL: Making SQL Easier to Infer from Natural Language Specifications
https://github.com/ygan/spider-dk
공식 코드Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization
https://github.com/ygan/spiderss-spidercg
공식 코드Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment
https://github.com/yizhang-unifr/xmode
공식 코드Explainable Multi-Modal Data Exploration in Natural Language via LLM Agent
https://github.com/yushi-hu/ic-dst
공식 코드https://github.com/zhanzecheng/IRNet
공식 코드Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
https://github.com/zhanzecheng/IRNet-1
공식 코드Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
https://github.com/zhshlii/petsql
공식 코드PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency
https://github.com/zhxlia/murre
공식 코드MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL
https://github.com/zirui-HIT/DAC
공식 코드https://github.com/zirui-HIT/Fused
공식 코드Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/esm
ESM+: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models
https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/graphix
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
https://github.com/AlisonYao/NLP-Final-Project
TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation
https://github.com/Aprilkaka/nonlocal_mindspore
https://github.com/Baidi96/text2sql
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
https://github.com/BorealisAI/DT-Fixup
https://github.com/BroCoLySTyLe/SQLovaReview
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
https://github.com/CX000/sqlnet_inference_py36
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
https://github.com/CurryTang/Graph-LLM
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.