SQL Parsing
21 papers with code • 8 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in SQL Parsing
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
IMDb Movie Reviews
ATIS
Yelp
Most implemented papers
KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers
The goal of database question answering is to enable natural language querying of real-life relational databases in diverse application domains.
Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing
alibabaresearch/damo-convai
•
•
The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i. e., properly recognizing mentions of unseen columns or tables when generating SQLs.
Improving Text-to-SQL Evaluation Methodology
jkkummerfeld/text2sql-data
•
•
ACL 2018
Second, we show that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries; therefore, we propose a complementary dataset split for evaluation of future work.
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
benbogin/spider-schema-gnn
•
•
ACL 2019
Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time.
Global Reasoning over Database Structures for Text-to-SQL Parsing
benbogin/spider-schema-gnn-global
•
•
IJCNLP 2019
State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time.
A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing
sanxing-chen/linking-tale
•
•
COLING 2020
In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and the SQL query to the structured knowledge in the database.
Optimizing Deeper Transformers on Small Datasets
BorealisAI/DT-Fixup
•
•
ACL 2021
This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing
PaddlePaddle/Research
•
•
EMNLP 2021
For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries.
Learning to Synthesize Data for Semantic Parsing
berlino/tensor2struct-public
•
•
NAACL 2021
Moreover, explicitly modeling compositions using PCFG leads to a better exploration of unseen programs, thus generate more diverse data.
Weakly Supervised Text-to-SQL Parsing through Question Decomposition
tomerwolgithub/question-decomposition-to-sql
•
•
Findings (NAACL) 2022
Given questions, their QDMR structures (annotated by non-experts or automatically predicted), and the answers, we are able to automatically synthesize SQL queries that are used to train text-to-SQL models.
