Awesome Sequence to SQL and Semantic Parsing
Semantic parsing (SP) is one of the most important tasks in natural language processing (NLP). It requires both understanding the meaning of natural language sentences and mapping them to meaningful executable queries such as logical forms, SQL queries, and Python code.
This field has been studied for decades mainly from both NLP and Database communities. Here is a short curated list of resources for semantic parsing and sequence to SQL (seq2sql).
Please feel free to email Tao Yu (firstname.lastname@example.org).
- SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task
- Zero-shot Parser: Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing
- A Detailed Analysis of WikiSQL: What It Takes to Achieve 100% Condition Accuracy on WikiSQL
- Coarse2fine: Coarse-to-Fine Decoding for Neural Semantic Parsing
- SQL Evaluation Methodology: Improving Text-to-SQL Evaluation Methodology
- User Feedback via Dialog: DialSQL: Dialogue Based Structured Query Generation
- Involving Context in the Task: Learning to Map Context-Dependent Sentences to Executable Formal Queries
- TypeSQL: TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation
- SQLNet: SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- Seq2SQL: Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- Syntactic Neural Models: A Syntactic Neural Model for General-Purpose Code Generation, Abstract Syntax Networks for Code Generation and Semantic Parsing
- NL2SQL: Learning a Neural Semantic Parser from User Feedback
- Seq2Tree: Learning a Neural Semantic Parser from User Feedback
- NaLIR: Constructing an Interactive Natural Language Interface for Relational Databases
- Paraphrase: Cross-domain Semantic Parsing via Paraphrasing
- NL2WebAPI: Building Natural Language Interfaces to Web APIs
Talks, Blogs, or Books
- Spider: One More Step Towards Natural Language Interfaces to Databases
- How to Talk to Your Database
- ACL 2018 Tutorial on Neural Semantic Parsing
- Natural Language Data Management and Interfaces
- A Syntactic Neural Model for General-Purpose Code Generation
- Learning to Map Context-Dependent Sentences to Executable Formal Queries
- Spider: a large-scale complex and cross-domain semantic parsing and text-to-SQL dataset
- 8 traditional single datasets: ATIS, GeoQuery, Academic, Advising, Scholar etc.
- More on NLP progress page