... levels in the language processing area such as lexical ac-quisition, information retrieval, machine trans-lation, speech processing, etc. Furthermore thesimilar problem also occurs in the ... languageprocessing relies on manually created dictionar-ies, which have inconsistencies in defining wordunits and limitation in the quantity. [1] proposeda word extraction algorithm employing C4.5with ... some string features such as entropy andmutual information. They reported a result of 85% in precision and 50% in recall measures.For word segmentation, the longest matching,maximal matching and...