# ConTrOn: Continuously Trained Ontology based on Technical Data Sheets and Wikidata

## TL;DR

ConTrOn is a system that automatically enriches ontologies with data from technical data sheets and external knowledge bases, enhancing automated information extraction in engineering contexts.

## Contribution

It introduces a method for continuously augmenting ontologies by integrating data sheet information with external sources like Wikidata, improving knowledge accumulation over time.

## Key findings

- Significant increase in information extraction accuracy after ontology enrichment
- Effective integration of data sheets with external knowledge bases
- Demonstrated improvements in spacecraft parts data processing

## Abstract

In engineering projects involving various parts from global suppliers, one common task is to determine which parts are best suited for the project requirements. Information about specific parts' characteristics is published in so called data sheets. However, these data sheets are oftentimes only published in textual form, e.g., as a PDF. Hence, they have to be transformed into a machine-interpretable format. This transformation process still requires a lot of manual intervention and is prone to errors. Automated approaches make use of ontologies to capture the given domain and thus improve automated information extraction from the data sheets. However, ontologies rely solely on experiences and perspectives of their creators at the time of creation and cannot accumulate knowledge over time on their own. This paper presents ConTrOn -- Continuously Trained Ontology -- a system that automatically augments ontologies. ConTrOn tackles terminology problems by combining the knowledge extracted from data sheets with an ontology created by domain experts and external knowledge bases such as WordNet and Wikidata. To demonstrate how the enriched ontology can improve the information extraction process, we selected data sheets from spacecraft development as a use case. The evaluation results show that the amount of information extracted from data sheets based on ontologies is significantly increased after the ontology enrichment.