CORPUS-BASED TERMS EXTRACTION IN LINGUISTICS DOMAIN FOR INDONESIAN LANGUAGE

Abstract

This research aims to extract the mono-lexical and poly-lexical terms from linguistics domain in Indonesian language. As the terminology and lexicology concept is somehow blurry, this research applies CTT by Cabré to do the terms extraction procedure. The corpus-based terminology method is applied in this research to get the best mono-lexical and poly-lexical terms possible. To compile the general and the specialized corpus in this research, AntConc is applied as an instrument. Even though the result is noisy, further analysis about the term limitation manually makes this research semi-automatic. The result shows that the limitation in language and words structure helps this research to delimit the mono-lexical terms extracted in this research. Furthermore, the mono-lexical terms extracted act as the starting point for poly-lexical terms.