摘要
本文主要介绍中国传媒大学计算语言学博士生们从依存树库中获取语言学知识的一些工作，如汉语复杂网络的研究等。这些工作都是在汉语依存树库的基础上进行的。本文也简要地介绍了国外从语料库中获取非语言学知识的研究以及信’息自动抽取的研究。作者认为从语料库挖掘知识和抽取信息应当是现代语言学研究的基本方法。
This paper describes the discoveries of the complex network of the Chinese language by the doctoral students at Communication University of China. Their work was based on the Chinese dependency Treebank. Also, it introduces cases of nonlinguistic knowledge mining and automatic information extraction by scholars abroad. The writer holds that linguistic studies should be based on knowledge mining and automatic information extraction.
出处
《外语与外语教学》
CSSCI
北大核心
2010年第4期1-7,共7页
Foreign Languages and Their Teaching
关键词
语料库
依存树库
知识挖掘
信息抽取
corpus
dependency Treebank
knowledge mining
information extraction
