Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers
Abhijeet Awasthi, Soumen Chakrabarti, Sunita Sarawagi
Abstract
Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cases) from the new domain at the encoder’s input in a Seq-to-Seq model. Such methods cannot adequately leverage the structure of logical forms in the case examples. We propose StructCBR, a structured case-based reasoning approach, which leverages subtree-level similarity between logical forms of cases and candidate outputs, resulting in better decoder decisions. For the task of adapting Text-to-SQL models to unseen schemas, we show that exploiting case examples in a structured manner via StructCBR offers consistent performance improvements over prior inference-time adaptation methods across five different databases. To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.
BibTeX
@article{Awasthi_Chakrabarti_Sarawagi_2023, title={Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26476}, DOI={10.1609/aaai.v37i11.26476}, abstractNote={Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cases) from the new domain at the encoder’s input in a Seq-to-Seq model. Such methods cannot adequately leverage the structure of logical forms in the case examples. We propose StructCBR, a structured case-based reasoning approach, which leverages subtree-level similarity between logical forms of cases and candidate outputs, resulting in better decoder decisions. For the task of adapting Text-to-SQL models to unseen schemas, we show that exploiting case examples in a structured manner via StructCBR offers consistent performance improvements over prior inference-time adaptation methods across five different databases. To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Awasthi, Abhijeet and Chakrabarti, Soumen and Sarawagi, Sunita}, year={2023}, month={Jun.}, pages={12536-12544} }