Ontologies are computational artifacts to represent knowledge through classes and relations between them. Those knowledge bases require a lot human effort to be constructed due to the need of domain experts and knowledge engineers. Ontology Learning aims to automatically build ontologies from data that can be from multimedia, web pages, databases, unstructured text, etc. In this work, we propose a methodology to automatically build an ontology to represent concepts map of subjects to be used in academic context. The main contribution of this methodology is that does not require handcrafted features by using Deep Learning techniques to identify taxonomic and semantic relations between concepts of some specific domain. Also, due the implementation of transfer learning is not needed of specific domain dataset, the relation classification model is trained with Wikipedia and WordNet by distant supervision technique and the knowledge is transferred to a specific domain by word embedding techniques. The results of this approach are promising considering the lack of human intervention and feature engineering.
CITATION STYLE
Navarro-Almanza, R., Juárez-Ramírez, R., Licea, G., & Castro, J. R. (2020). Automated Ontology Extraction from Unstructured Texts using Deep Learning. In Studies in Computational Intelligence (Vol. 862, pp. 727–755). Springer. https://doi.org/10.1007/978-3-030-35445-9_50
Mendeley helps you to discover research relevant for your work.