Bridging Textual Data and Conceptual Models: A Model-Agnostic Structuring Approach
By: Jacques Chabin, Mirian Halfeld Ferrari, Nicolas Hiot
We introduce an automated method for structuring textual data into a model-agnostic schema, enabling alignment with any database model. It generates both a schema and its instance. Initially, textual data is represented as semantically enriched syntax trees, which are then refined through iterative tree rewriting and grammar extraction, guided by the attribute grammar meta-model \metaG. The applicability of this approach is demonstrated using clinical medical cases as a proof of concept.
Similar Papers
Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
Computation and Language
Turns messy writing into organized information for smarter AI.
A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs
Databases
Connects different computer data for businesses.
From Conceptual Data Models to Multimodal Representation
Artificial Intelligence
Helps computers understand and show information better.