Large-scale Taxonomy Induction Using Entity and Word Embeddings
This addresses the costly manual effort in taxonomy construction for knowledge organization in intelligent systems, though it appears incremental as it builds on existing embeddings and databases.
The paper tackled the problem of automatically building large-scale taxonomies by proposing TIEmb, an unsupervised method using entity and text embeddings to extract class subsumption axioms from knowledge bases, and applied it to the WebIsA database to extract hierarchies in the Person and Place domains.
Taxonomies are an important ingredient of knowledge organization, and serve as a backbone for more sophisticated knowledge representations in intelligent systems, such as formal ontologies. However, building taxonomies manually is a costly endeavor, and hence, automatic methods for taxonomy induction are a good alternative to build large-scale taxonomies. In this paper, we propose TIEmb, an approach for automatic unsupervised class subsumption axiom extraction from knowledge bases using entity and text embeddings. We apply the approach on the WebIsA database, a database of subsumption relations extracted from the large portion of the World Wide Web, to extract class hierarchies in the Person and Place domain.