On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries
This work addresses the challenge of enhancing supervised semantic parsing for SQL generation, offering incremental improvements through richer supervision for researchers and practitioners in natural language processing.
The authors tackled the problem of improving semantic parsing to SQL queries by introducing a dataset with fine-grained alignments between questions and SQL fragments, and proposed two training methods that increased execution accuracy by 4.4% over baselines, with potential gains up to 23.9% indicated by oracle experiments.
Large-scale semantic parsing datasets annotated with logical forms have enabled major advances in supervised approaches. But can richer supervision help even more? To explore the utility of fine-grained, lexical-level supervision, we introduce Squall, a dataset that enriches 11,276 WikiTableQuestions English-language questions with manually created SQL equivalents plus alignments between SQL and question fragments. Our annotation enables new training possibilities for encoder-decoder models, including approaches from machine translation previously precluded by the absence of alignments. We propose and test two methods: (1) supervised attention; (2) adopting an auxiliary objective of disambiguating references in the input queries to table columns. In 5-fold cross validation, these strategies improve over strong baselines by 4.4% execution accuracy. Oracle experiments suggest that annotated alignments can support further accuracy gains of up to 23.9%.