KOCP, KAIST Oxford Concordance Program, is designed and implemented. KOCP makes indexes, concordances, wordlists and statistics from Korean and English texts.
The system consists of affix split, stop-word elimination, and synonym replacement processing for language normalization. Phrase and word stem tables are also used.
This system can be used for dictionary construction, style analysis, and automatic indexing for text retrieval. For text retrieval, good indexes can be obtained using reasonable stop-word and Phrase tables.
