Discourse Tree Ontology Construction via Rhetorical Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated ontology construction techniques are limited in creating comprehensive and accurate ontologies, relying heavily on human collaboration and are not effective in leveraging rich discourse-related information, resulting in inferior performance in applications such as search systems, recommendation systems, and decision support systems.
Innovation Solution
The use of discourse techniques to generate and extend ontologies by constructing discourse trees that represent rhetorical relationships between text fragments, identifying central entities, and forming generalized phrases and tuples, which are then converted into logical representations to update the ontology, enabling improved automated agents and more accurate knowledge representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated ontology construction techniques are used, then productivity is improved, but the quality and comprehensiveness of the ontology is insufficient
Solution Approach 1:
The patent introduces discourse trees as an intermediary structure between raw text and ontology. The discourse tree analyzes rhetorical relationships between text fragments, identifies central entities, and organizes information hierarchically before converting to ontology entries. This intermediary layer enables automated systems to process complex discourse structures and generate high-quality ontologies that capture nuanced relationships.
Solution Approach 2:
The patent replaces manual ontology construction methods with automated computational processes. The system automatically parses text, builds discourse trees, identifies central entities, extracts tuples, and generates ontology entries without human intervention. This substitution of mechanical manual work with automated computational mechanisms significantly improves productivity while maintaining quality through sophisticated algorithms.
2Reliability
If human collaboration is relied upon for ontology construction, then ontology quality is improved, but productivity and automation extent are reduced
Solution Approach 1:
The patent implements self-service automation where the system autonomously performs the entire ontology construction process. The automated agent independently parses input text, constructs discourse trees, identifies central entities, extracts tuples, and generates ontology entries without requiring human collaboration or intervention. This self-service capability achieves full automation while maintaining high ontology quality through sophisticated computational methods.
3Device complexity
If discourse-related information is not leveraged, then processing simplicity is maintained, but ontology comprehensiveness and accuracy are insufficient
Solution Approach 1:
The patent segments the text into elementary discourse units (EDUs) and organizes them into discourse trees based on rhetorical relationships. This segmentation allows the system to process complex discourse structures systematically, identifying central entities and extracting relevant information from each segment. The hierarchical organization of segments enables comprehensive ontology generation while maintaining manageable processing complexity.
Solution Approach 2:
The patent adds a new dimensional layer of analysis by constructing discourse trees that represent rhetorical relationships between text fragments. This additional dimension of discourse structure analysis enables the system to capture nuanced relationships and comprehensive information that would otherwise be lost in simple text processing, thereby increasing ontology comprehensiveness without proportionally increasing processing complexity.
Data Source
AI summary
Systems, devices, and methods of the present invention involve discourse trees. In an example, a method involves generating a discourse tree. The method includes identifying, from the discourse tree, a central entity that is associated with a rhetorical relation of type elaboration and corresponds to a topic node that identifies a central entity of the text. The method includes determining a subset of elementary discourse units of the discourse tree that are associated with the central entity. The method includes forming generalized phrases from the subset of elementary discourse units. The method includes forming tuples from the generalized phrases, where a tuple is an ordered set of words in normal form. The method involves responsive to successfully converting an elementary discourse unit associated with an identified tuple into a logical representation, updating the ontology with an entity from the identified tuple.