摘要
讨论了自然语言理解应用于智能搜索和信息提取的若干问题,阐述了标注、完善基于词典的知识库的处理手段,特别是语料库语言学在这些环节的应用情况。同时,对中文信息提取涉及的技术难点和信息提取的实现过程也作了较为详尽的论述。
This thesis dissertated several problems about the application of natural language processing in intelligent searching and information extraction, and dissertated the following questions of labeling information and perfecting the technology of repository based on dictionary, especially the problems about the application of Corpus Linguistics in the processing.At the same time, this thesis dissertated detailedly the technology nodus and the realization of information extraction.
出处
《计算机应用研究》
CSCD
北大核心
2004年第2期14-16,共3页
Application Research of Computers
基金
国家重点基础研究发展规划"973"资助项目
关键词
智能搜索
信息提取
标注
Intelligent Searching
Information Extraction
Labeling Information
