This paper aims to describe a text-mining approach on a domain-specific corpus (cork) within the theoretical framework of the dual dimension of terminology. The objective is to construct a terminological dictionary and align it with an ontology. We will discuss various aspects, including (i) domain specificities; (ii) lexical markers; (iii) automatic corpus processing using Sketch Engine; (iv) representation of lexical networks through CmapTools; and (v) representation of the concept system using Protégé. The ontology’s aim is to provide logical support for the coherence and quality of the natural language definitions included in the terminological resource.