Back to Search
Start Over
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
- Publication Year :
- 2020
- Publisher :
- arXiv, 2020.
-
Abstract
- We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data. We construct synthetic question-SQL pairs over high-quality tables via a synchronous context-free grammar (SCFG) induced from existing text-to-SQL datasets. We pre-train our model on the synthetic data using a novel text-schema linking objective that predicts the syntactic role of a table field in the SQL for each question-SQL pair. To maintain the model's ability to represent real-world data, we also include masked language modeling (MLM) over several existing table-and-language datasets to regularize the pre-training process. On four popular fully supervised and weakly supervised table semantic parsing benchmarks, GraPPa significantly outperforms RoBERTa-large as the feature representation layers and establishes new state-of-the-art results on all of them.<br />Comment: 16 pages; Accepted to ICLR 2021
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....40b2daa982b77ef42d62ed655c7d85a9
- Full Text :
- https://doi.org/10.48550/arxiv.2009.13845