Using Recurrent Neural Network for Learning Expressive Ontologies
This work addresses ontology learning for AI and knowledge representation, but it appears incremental as it applies an existing method (RNN) to a new domain without reported gains.
The authors tackled the problem of ontology learning by proposing a Recurrent Neural Network-based system to leverage neural networks' effectiveness in natural language processing tasks, but no concrete results or numbers are provided in the abstract.
Recently, Neural Networks have been proven extremely effective in many natural language processing tasks such as sentiment analysis, question answering, or machine translation. Aiming to exploit such advantages in the Ontology Learning process, in this technical report we present a detailed description of a Recurrent Neural Network based system to be used to pursue such goal.