Segmenting a sentence into morphemes using statistic information between words

This paper is on dividing non-separated language sentences (whose words are not separated from each other with a space or other separaters) into morphemes using statistical information, not grammatical information which is often used in NLP. In this paper we describe our method and experimental result on Japanese and Chinese sentences. As will be seen in the body of this paper, the result shows that this system is efficient for most of the sentences.