基于既定词表的自适应汉语分词技术研究 - 田野的羽毛 - 博客园 关键词] 自动分词 新词识别 未登录词 [gap=735]Keywords] automatic segmentation; new word identification; unlisted words
基于8个网页-相关网页
The existence of unlisted words seriously affects the accuracy and speed of automatic segmentation of Chinese words.
未登录词的存在严重影响了汉语自动分词与自动标引的准确率和速率。
At present, the unlisted words remains affect the efficiency of information retrieval and automatic indexing largely.
目前未登录词问题仍然很大程度上影响着自动标引和信息检索的效率。
Based on language data of dialect of unlisted words, this thesis conducts a statistical data so as to explain the features of them.
以数据库为基础，对新词语中的方言词语从来源、领域、语音、语义、语法等方面进行统计研究，发现进入普通话的方言词语的特征。
应用推荐