Semantic Parsing in Context (SParC)
Semantic ParsingSQL-to-TextEnglishBenchmark
The Semantic Parsing in Context (SParC) dataset is a English semantic parsing resource from Yu et al. at 2019 comprising 4,298 examples.
📊 This dataset is used as an LLM benchmark. See model leaderboards →
About Semantic Parsing in Context (SParC)
Dataset consists of 4,298 coherent question sequences (12k+ unique individual questions annotated with SQL queries annotated byt. It is the context-dependent/multi-turn version of the Spider task.
Details
- Task
- Semantic Parsing, SQL-to-Text
- Language
- English
- Format
- JSON, SQL
- Rows / instances
- 4,298
- Creator
- Yu et al.
- Year
- 2019