Development of a Unified Output Format for Text Parsers in the Ontology Construction System From Text Documents

The challenge of effectively constructing ontologies from text documents remains unresolved, posing a critical gap in modern knowledge extraction methodologies. One of the primary obstacles is the lack of a standardized output format across different NLP tools, particularly text parsers, which serve as the foundational step in multi-stage knowledge extraction processes. While several widely used text parsers exist, each excels in specific functions, making it beneficial to leverage multiple parsers for more comprehensive ontology construction. However, this approach introduces the issue of reconciling their disparate output formats.
To address this challenge, we propose using a graph database to store parser outputs in a subject- predicate-object triple format, enabling seamless integration and further processing through rule-based transformations using SPARQL queries. A key advantage of this approach is the ability to execute new transformation rules dynamically, allowing for greater flexibility and efficiency in ontology generation.
As part of our research, we developed an intelligent agent in Java capable of constructing semantic graphs from natural language text using a rule-based approach. The agent was employed to evaluate the relationship between the execution time of syntax-semantic transformation rules and variables such as text corpus size and dataset sample dimensions. This evaluation was made possible through the implementation of first-level reflection for the studied transformation rule.
The results demonstrate that our approach – standardizing parser outputs via a graph database – roves effective in terms of both computational complexity and processing speed. By streamlining the ontology construction process, our method paves the way for advanced automated learning of intelligent agents based on textual information, unlocking new possibilities for modern science in the realm of knowledge extraction and representation.