摘要
探讨了基于无指导学习策略和无词表条件下的汉语自动分词方法,结合中文分词过程,在自动进行中文分词的结果之上,自动提取文本中特定出现频率以上的高频词条,将这些词条作为辅助翻译预处理阶段任务分配的重要依据,从而有效提高了辅助翻译平台预处理过程中的任务分配效率及任务分配准确率。
This paper introduces the automatic word segmentation based on non-guidance study strategy and statistical model.Utilize the result of word segmentation to extracts high-frequency words in the text.The high-frequency words extracted will be the important basis of task allocation in the stage of pretreatment of Computer-aid translation.This method have improved validity and scientific of task allo-cation in the stage of pretreatment of Computer-aid translation.
作者
吴树国
刮俊杰
WU Shu-guo,GUA Jun-jie(College of Computer Science and Technology,Beijing University of Technology,Beijing 100124,China)
出处
《电脑知识与技术》
2008年第12X期2796-2798,共3页
Computer Knowledge and Technology
关键词
信息提取
中文分词
高频词提取
机器翻译
辅助翻译
information retrieval Chinese Segmentation
Extraction of high-frequency word
Machine translation
Translation Memory