摘要
提出了一个改进的书面汉语全切分算法,它通过确保每次切分位置的唯一性,克服了全切分中普遍存在的重复切分。实验证明,改进后的全切分算法效率平均提高80%以上。
An improved algorithm of word omni-segmentation for written Chinese is proposed in this paper,which overcomes the repetitive word segmentation by controlling a unique position where segmentation begins. An experiment proves an increase of 80% in efficiency.
关键词
切分
全切分
重复切分
word segmentation of written Chinese
omni-segmentation
repetitive word segmentation
