2017/03/30 by Hasan M. Jamil, Jamil, Hasan M.
Biochemistry, Genetics and Molecular Biology · Computer Science · #Biomedical Text Mining and Ontologies #Databases (cs.DB) #FOS: Computer and information sciences #Natural Language Processing Techniques #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.1703.10692
openalex publication_date 2017/03/30 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28
Increasingly, keyword, natural language and NoSQL queries are being used for\ninformation retrieval from traditional as well as non-traditional databases\nsuch as web, document, image, GIS, legal, and health databases. While their\npopularity are undeniable for obvious reasons, their engineering is far from\nsimple. In most part, semantics and intent preserving mapping of a well\nunderstood natural language query expressed over a structured database schema\nto a structured query language is still a difficult task, and research to tame\nthe complexity is intense. In this paper, we propose a multi-level\nknowledge-based middleware to facilitate such mappings that separate the\nconceptual level from the physical level. We augment these multi-level\nabstractions with a concept reasoner and a query strategy engine to dynamically\nlink arbitrary natural language querying to well defined structured queries. We\ndemonstrate the feasibility of our approach by presenting a Datalog based\nprototype system, called BioSmart, that can compute responses to arbitrary\nnatural language queries over arbitrary databases once a syntactic\nclassification of the natural language query is made.\n