《Table 1 Part-of-speech tagging of named entity in ANSJ》

  提示：宽带有限、当前游客访问压缩模式

本系列图表出处文件名：随高清版一同展现

《Hierarchical clustering based on single-pass for breaking topic detection and tracking》

1. 获取 高清版本忘记账户？点击这里登录

1. 下载图表忘记账户？点击这里登录

For each report，named-entity vector space model（NE-VSM）is applied.The weight of feature vector is calculated by named-entity identified term frequencyinverse document frequency（ITF-IDF），which is an improved version of basic TF-IDF.Named entities are identified by several POS tags shown in Table 1.