2022
EMNLP
EMNLP 2022
Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge
Abstract
AbstractIn this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by representing formulaic knowledge rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2% improvement overall on KnowSQL.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— formulaic knowledge
🐣
Hot Topic Early Bird
— domain knowledge
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Application Areas > Domain Adaptation
Natural Language Processing > Understanding > Semantic Analysis
Artificial Intelligence > Core AI > Knowledge Editing
Natural Language Processing > Applications > Semantic Parsing
Deep Learning > Learning Types > Retrieval-Augmented Generation
Artificial Intelligence > Core AI > Knowledge