Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences

Rie Kubota Ando Lillian Lee Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences http://arxiv.org/abs/cs.CL/0205009 2002 CoRR cs.CL/0205009 db/journals/corr/corr0205.html#cs-CL-0205009 informal publication