OpenCodePapers

semantic-parsing-on-spider

Semantic Parsing
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL✓ Link84.1RESDSQL-3B + NatSQL2023-02-12
LEVER: Learning to Verify Language-to-Code Generation with Execution✓ Link81.9code-davinci-002 175B (LEVER)2023-02-16
RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL✓ Link75.5RASAT+PICARD2022-05-14
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing✓ Link74.0Graphix-3B + PICARD2023-01-18
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models✓ Link71.9 T5-3B + PICARD2021-09-10
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL✓ Link70.1SADGA + GAP2021-11-01
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training✓ Link69.7RATSQL + GAP2020-12-18
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing✓ Link69.6RATSQL + Grammar-Augmented Pre-Training2020-09-29
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers✓ Link65.6RATSQL + BERT2019-11-10
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task✓ Link19.7Exact Set Matching2018-09-24
Check out how to contribute new results.