Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation
arXiv:2502.11201v3 Announce Type: replace-cross Abstract: NoSQL databases are core data infrastructure, yet natural-language access to them remains underdeveloped: correct query generation must recover how a non-relational data model represents entities, nested paths, arrays, missing fields, and dynamic keys. This paper studies Text-to-NoSQL, translating natural-language requests into executable NoSQL queries, instantiated with MongoDB aggregation pipelines over schema-less document stores. We present TEND, short for Text-to-NoSQL Dataset, an execution-verified benchmark with 1,210 MongoDB-nat
The proliferation of NoSQL databases as core data infrastructure combined with rapid advancements in natural language processing makes this development timely and critical.
This breakthrough promises to democratize access to complex NoSQL data for non-technical users, accelerating data utilization and decision-making across various industries.
Traditional reliance on specialized database administrators for crafting complex NoSQL queries will diminish, enabling direct natural language interaction with NoSQL data stores.
- · Businesses using NoSQL databases
- · Data analysts and scientists
- · MongoDB and similar NoSQL vendors
- · AI agent developers
- · Database administrators focused solely on manual NoSQL query writing
- · Companies slow to adopt NLP-driven data access tools
Non-technical users can interact directly with complex NoSQL databases using natural language.
This reduces friction in data access, leading to faster insights and potentially new applications built on readily available data.
The integration of such capabilities into AI agents could create highly autonomous systems capable of dynamic data retrieval and analysis without human intervention.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI