Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers
Keywords:SNLP: Lexical & Frame Semantics, Semantic Parsing, SNLP: Question Answering
AbstractInference-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.
How to Cite
Awasthi, A., Chakrabarti, S., & Sarawagi, S. (2023). Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 12536-12544. https://doi.org/10.1609/aaai.v37i11.26476
AAAI Technical Track on Speech & Natural Language Processing