Tools for sublanguage based semantic knowledge acquisition from corpora

Abstract

This paper describes the implantation of a KA tool kit for use with sublanguage-specific corpora. The key idea of KA as an evolutionary process is discussed in detail. Special attention is paid to the system's attempt to avoid the pitfalls faced by purely statistical KA processes, The system relies on a set of interactively linked subprocesses and on a central knowledge base which stores all acquired knowledge.