The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Onto.KOM Towards a Minimally Supervised Ontology Learning System based on Word Embeddings and Convolutional Neural Networks

Author:Wael Alkhatib, Leon Alexander Herrmann, Christoph Rensing
Date:August 2017
Kind:In proceedings - use for conference & workshop papers
Book title:Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management
Keywords:Ontology, Neural Language Model, Word Embeddings, Ontology Enrichment, Convolutional Neural Network, Deep Learning.
Research Area(s):Knowledge Media
Abstract:This paper introduces Onto.KOM: a minimally supervised ontology learning system which minimizes the reliance on complicated feature engineering and supervised linguistic modules for constructing the different consecutive components of an ontology, potentially providing domain independent and fully automatic ontology learning system. The focus here is to fill in the gap between automatically identifying the different ontological categories reflecting the domain of interest and the extraction and classification of semantic relations between the concepts under the different categories. In Onto.KOM, we depart from traditional approaches with intensive linguistic analysis and manual feature engineering for relation classification by introducing a convolutional neural network (CNN) that automatically learns features from word-pair offset in the vector space. The experimental results show that our system outperforms the state-of-the-art systems for relation classification in terms of F1-measure.

If the paper is not available from this page, you might contact the author(s) directly via the "People" section on our KOM Homepage.

[Export this entry to BibTeX]