Hybrid NER Ontology Mapping for Synonym Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Named entity recognition (NER) processes face challenges in efficiently linking synonyms and mapping concepts to ontological standards, particularly due to high computational intensity, laboriousness, and inherent false positives, which complicate downstream data curation and search functionalities.
Innovation Solution
A method that automatically learns new synonyms for concepts, maps raw NER outputs to ontological concepts, accounts for false positives, and aggregates results from machine learning and rule-based approaches to provide a hybrid solution, utilizing processor-based techniques for acronym expansion, string matching, and ontology-specific screening to generate confidence scores and index associations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual curation techniques are used to link synonyms and map concepts to ontologies, then accuracy is improved, but productivity deteriorates due to laboriousness and time consumption
Solution Approach 1:
The system performs self-service by automatically learning synonyms and mapping concepts to ontologies without requiring manual human curation. The NER process combined with ontology mapping algorithms enables the system to autonomously identify entities, learn synonymous terms, and map them to standardized ontology concepts, thereby maintaining high accuracy while eliminating laborious manual work
Solution Approach 2:
The patent replaces the mechanical manual curation process with an automated computational system. Instead of human experts manually identifying synonyms and mapping concepts, the system uses NER algorithms, vectorization techniques, and ontology mapping processes to automatically perform these tasks, substituting human mechanical effort with automated computational mechanisms
2Productivity
If automated NER processes are used to extract entities, then productivity is improved, but reliability deteriorates due to false positives
Solution Approach 1:
The system implements feedback mechanisms where the NER process outputs are evaluated against ontology constraints and consistency rules. The mapping process provides feedback by identifying when extracted entities do not conform to expected ontology structures, allowing the system to detect and correct false positives while maintaining high extraction speed
Solution Approach 2:
The patent applies preliminary anti-action by incorporating false positive detection and filtering steps before final entity output. The system proactively identifies potential false positives through ontology consistency checking and confidence scoring, preventing erroneous entities from being propagated to downstream processes
3Adaptability or versatility
If comprehensive synonym linking is performed for all NER outputs, then adaptability is improved, but device complexity increases due to computational intensity
Solution Approach 1:
The system applies partial action by performing synonym learning and ontology mapping selectively rather than exhaustively for all possible entity pairs. The NER process focuses on identifying relevant entities with sufficient confidence, and ontology mapping is performed for entities that meet specific criteria, avoiding unnecessary computational overhead while maintaining comprehensive coverage for important cases
Data Source
AI summary
This disclosure enables various technologies that can (1) learn new synonyms for a given concept without manual curation techniques, (2) relate (e.g., map) some, many, most, or all raw named entity recognition outputs (e.g., “United States”, “United States of America”) to ontological concepts (e.g., ISO-3166 country code: “USA”), (3) account for false positives from a prior named entity recognition process, or (4) aggregate some, many, most, or all named entity recognition results from machine learning or rules based approaches to provide a best of breed hybrid approach (e.g., synergistic effect).