48 papers with code • 2 benchmarks • 8 datasets

( Image credit: SyntaxSQLNet )

Greatest papers with code

IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation

PaddlePaddle/PaddleNLP EMNLP 2020

Our model outperforms previous state-of-the-art model by a large margin and achieves new state-of-the-art results on the two datasets.


RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers

PaddlePaddle/PaddleNLP ACL 2020

The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query.

Semantic Parsing Text-To-Sql

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising

salesforce/WikiSQL 17 May 2021

In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture.

Denoising Slot Filling +1

SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Language

salesforce/WikiSQL 7 Nov 2020

We explore using T5 (Raffel et al. (2019)) to directly translate natural language questions into SQL statements.

Text Generation Text-To-Sql

SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning

salesforce/WikiSQL ICLR 2018

Existing state-of-the-art approaches rely on reinforcement learning to reward the decoder when it generates any of the equivalent serializations.


Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations

google-research/language 15 Apr 2021

Sequence-to-sequence (seq2seq) models are prevalent in semantic parsing, but have been found to struggle at out-of-distribution compositional generalization.

Semantic Parsing Text-To-Sql

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

facebookresearch/tabert ACL 2020

Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks.

Semantic Parsing Text-To-Sql

Semantic Evaluation for Text-to-SQL with Distilled Test Suites

taoyds/spider EMNLP 2020

We propose test suite accuracy to approximate semantic accuracy for Text-to-SQL models.


Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

taoyds/spider EMNLP 2018

We define a new complex and cross-domain semantic parsing and text-to-SQL task where different complex SQL queries and databases appear in train and test sets.

Semantic Parsing Text-To-Sql