Automated Domain Taxonomy Extension via Glossary Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing domain taxonomies require manual updating, which is time-consuming, costly, and prone to errors, as they fail to capture the granularity of concepts present in glossaries within domain documents, impacting the accuracy of cognitive computing services.
Innovation Solution
A computer-based method that accesses an initial taxonomy, identifies glossaries in a domain corpus, extracts term-definition pairs, and maps terms into the taxonomy based on definitions to generate an updated taxonomy, leveraging techniques like head word extraction, tiny taxonomy building, and see also function to enhance granularity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual updating of domain taxonomy is performed, then taxonomy accuracy can be maintained, but time consumption and cost increase significantly
Solution Approach 1:
The system performs self-updating by automatically extracting terms from glossaries and mapping them to the taxonomy structure without requiring manual intervention. The computer executes automated processes to identify, extract, and integrate new terms, enabling the taxonomy to maintain itself autonomously while improving both accuracy and reducing time consumption.
Solution Approach 2:
The patent replaces the manual mechanical process of taxonomy updating with an automated computational system. The computer executes algorithms that automatically extract terms from glossaries, analyze definitions, map terms to appropriate taxonomy nodes, and update the structure, substituting human manual work with machine-based automated processing.
2Reliability
If manual updating of domain taxonomy is performed, then taxonomy accuracy can be maintained, but financial costs increase
Solution Approach 1:
The system performs self-updating by automatically extracting terms from glossaries and mapping them to the taxonomy structure without requiring manual intervention. The computer executes automated processes to identify, extract, and integrate new terms, enabling the taxonomy to maintain itself autonomously while improving both accuracy and reducing time consumption.
Solution Approach 2:
The patent replaces the manual mechanical process of taxonomy updating with an automated computational system. The computer executes algorithms that automatically extract terms from glossaries, analyze definitions, map terms to appropriate taxonomy nodes, and update the structure, substituting human manual work with machine-based automated processing.
3Reliability
If manual updating of domain taxonomy is performed, then taxonomy can be maintained, but error rate increases
Solution Approach 1:
The patent replaces the manual mechanical process of taxonomy updating with an automated computational system. The computer executes algorithms that automatically extract terms from glossaries, analyze definitions, map terms to appropriate taxonomy nodes, and update the structure, substituting human manual work with machine-based automated processing that reduces human error.
Solution Approach 2:
The system incorporates feedback mechanisms where the computer analyzes the extracted terms and definitions, validates mappings against the existing taxonomy structure, and adjusts the updating process based on the results. This feedback loop ensures accurate integration of new terms while maintaining taxonomy consistency and reducing errors.
4Measurement precision
If taxonomy granularity is extended to match glossary level, then cognitive computing accuracy improves, but device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the taxonomy extension process into distinct automated stages: extracting terms from glossaries, analyzing definitions, mapping terms to appropriate taxonomy nodes, and integrating new terms. This segmented approach manages complexity by breaking down the intricate task of granularity extension into systematic, computer-executable steps.
Solution Approach 2:
The patent replaces the manual mechanical process of taxonomy updating with an automated computational system. The computer executes algorithms that automatically extract terms from glossaries, analyze definitions, map terms to appropriate taxonomy nodes, and update the structure, substituting human manual work with machine-based automated processing.
Data Source
AI summary
A controller accesses an initial taxonomy for a domain comprising one or more existing terms for the domain identified in a hierarchical structure. The controller analyzes a corpus documents for a domain to identify a selection of one or more documents with glossaries. The controller extracts, from the glossaries, one or more pairs each comprising a term and a definition. The controller attempts to map a respective term of each of the one or more pairs into the initial taxonomy for the domain based on text of a respective definition of each of the one or more pairs to generate an updated taxonomy for the domain.