Semi-Supervised Instance Population of an Ontology using Word Vector Embeddings
This addresses the bottleneck of manual intervention in ontology population for information extraction and knowledge management systems, though it appears incremental.
The paper tackles the problem of manual ontology population by proposing a semi-supervised method using word embeddings, resulting in an ensemble model that outperforms individual models with improved accuracy.
In many modern day systems such as information extraction and knowledge management agents, ontologies play a vital role in maintaining the concept hierarchies of the selected domain. However, ontology population has become a problematic process due to its nature of heavy coupling with manual human intervention. With the use of word embeddings in the field of natural language processing, it became a popular topic due to its ability to cope up with semantic sensitivity. Hence, in this study, we propose a novel way of semi-supervised ontology population through word embeddings as the basis. We built several models including traditional benchmark models and new types of models which are based on word embeddings. Finally, we ensemble them together to come up with a synergistic model with better accuracy. We demonstrate that our ensemble model can outperform the individual models.