2020/09/16 by Victor W. Zhong, Zhong, Victor, Mike Lewis +5 · 6 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2009.07396
openalex publication_date 2020/09/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.