An approach to automated thesaurus construction using clusterization-based dictionary analysis

In the paper an automated approach for construction of the terminological thesaurus for a specific domain is proposed. It uses an explanatory dictionary as the initial text corpus and a controlled vocabulary related to the target lexicon to initiate extraction of the terms for the thesaurus. Subdivision of the terms into semantic clusters is based on the CLOPE clustering algorithm.

The approach diminishes the cost of the thesaurus creation by involving the expert only once during the whole construction process, and only for analysis of a small subset of the initial dictionary. To validate the performance of the proposed approach the authors successfully constructed a thesaurus in the cardiology domain.