A RULE-BASED METHOD FOR COMMAS DISAMBIGUATION IN CHINESE PATENT TEXT

摘要：

　　We described a rule-based method for disambiguating Chinese commas in patent text,which will be beneficial to the work on Chinese-English Patent MT.We annotated ten thousand sentences of patent text,and made a number of rules according to the annotated results.Experiments were conducted on 5 intact patent documents containing 1219 commas,and our model achieves an accuracy of over 90% overall.

关键词： Rule-based method Commas disambiguation Chinese patent text MT

作者: Qianqian Song Yun Zhu Lixia Wang Yaohong Jin

作者单位: Institute of Chinese Information Processing;CPIC-BNU Joint Laboratory of Machine Translation Beijing Normal University,Beijing 100875,China

会议类型: 国际会议

会议名称: 2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems (2012年第2届IEEE云计算与智能系统国际会议(IEEE CCIS2012))

会议地点: 杭州

会议语种:英文

页码: 1988-1992

在线出版日期: 2012-10-30（万方平台首次上网日期，不代表论文的发表时间）