TaBIIC: Taxonomy Building through Iterative and Interactive Clustering
This addresses the need for more refined and usable taxonomies in ontology building, though it appears incremental as it builds on existing approaches.
The paper tackles the problem of automatically building taxonomies from data, which often results in structures that are either too coarse or too fine-grained, by proposing an iterative and interactive method that combines pattern extraction and clustering. The result is a method applicable to various data sources, leading to taxonomies more directly integrable into ontologies.
Building taxonomies is often a significant part of building an ontology, and many attempts have been made to automate the creation of such taxonomies from relevant data. The idea in such approaches is either that relevant definitions of the intension of concepts can be extracted as patterns in the data (e.g. in formal concept analysis) or that their extension can be built from grouping data objects based on similarity (clustering). In both cases, the process leads to an automatically constructed structure, which can either be too coarse and lacking in definition, or too fined-grained and detailed, therefore requiring to be refined into the desired taxonomy. In this paper, we explore a method that takes inspiration from both approaches in an iterative and interactive process, so that refinement and definition of the concepts in the taxonomy occur at the time of identifying those concepts in the data. We show that this method is applicable on a variety of data sources and leads to taxonomies that can be more directly integrated into ontologies.