基础教育资源搜索引擎中的分词技术研究-教育技术学专业论文.docxVIP

ABSTRACTAutomatic ABSTRACT Automatic word segmentation is the basis of NLR Every Chinese information processing System based of Chinese word must depend word segmentation．The focus and difficult of Chinese word segmentation Me processing method船crossing-ambiguity word and unknown-word． On the base ofBERSE(Basic Education Resource Research Engine)projection．1 discussed the method ofChinese word segmentation in this paper． To resolve crossing—ambiguity word problem，1 found that the distinguishing feature for high frequency characteristic word and presented method to deal with crossing-ambiguity word，As support，we used character bi—gram for ambiguity resolution in Chinese word segmentation in the syStem implement． To identify Chinese name，I adopted resolution of statistic and regulation，used statistical measures，analyzed the character of name and Dresented method for sort．In system design，it can find Chinese name by the word segmentation fragment，experiments show that about 90％correct rate is achieved． In this paper,1 tried to find high frequency word resolution to unknown．words Word segmentation system count time of successful match and paper for high frequency,and then some weight to append these unknown—words into vocabulary．Therefore，the capacity of main vocabulary be extended automatically． m the end ofthis paper,the frame．flow and interface design ofChinese word segmentation system have been expatiated． Keywords：Chinese Information Process，Chinese word segmentation，crossing ambiguity, un-known word． 学位论文独创性声明本人郑踅疹骥： 学位论文独创性声明 本人郑踅疹骥： l、坚撼以“求实、刨裁”的季净学罐耱姨搴秘究王终。 2、本论文是我个人在导师撵譬下进弦鲍硪究工作翘取德艇科究 成果。 3、本论文中除弓|文外，所蠢实验、数据和有关材料均怒真实的。 4、本埝文中除引文和致谢的内容外，不包含獒他人或其它枫构 已经发表或撰写过的研究成聚。 5、其他弼志对本研究所做的贡献均已在论文中作了声明并表示 了谢意。 ， 作者签名： 瑗移簟 订 潮：—盘』：￡!堑—— 学位论文使用授权声明 本人宠全了蜒怒寨炻熬大学有关徐躲、镬用学位论文的蕊意，学 棱寅极缳整学位论文势自国家主管部门或菸攒定掘橡送交论文豹泡 子舨和纸矮敝；有投将学位论文用予非赢莘《晷的的少量复割并允许 论文进入学校图书馋被查耀；有权将学位论文鲍沟套壤入鸯关数援 库避行检索；有权将学位论文的标题和撼要汇撼出版。保密的学经 论文在解密后适用本媲定。 缓护 佟者签名： 嗣 掰： 日U舌1、研究背景 日U舌 1、研究背景 随着教育信息化的发展，Internet上的教育资源数量每年以几何级的