| 基于语料库和面向统计学的自然语言处理技术 |
| |
| 引用本文： | 周强.基于语料库和面向统计学的自然语言处理技术[J].计算机科学,1995(4). |
| |
| 作者姓名： | 周强 |
| |
| 作者单位： | 北京大学计算语言学研究所 北京 |
| |
| 摘 要： | 1引言 语料库语言学(Corpus Linguistics)是八十年代才崭露头角的一门新的计算语言学分支学科.它研究机器可读的自然语言文本的采集、存储、检索、统计、语法标注、句法语义分,以及具有上述功能的语料库在语言定量分析、词典编纂、作品风格分
|
An Introduction to the Corpus-Based, Statistics-Oriented Natural Language Processing Techniques |
| |
| Zhou Qiang.An Introduction to the Corpus-Based, Statistics-Oriented Natural Language Processing Techniques[J].Computer Science,1995(4). |
| |
| Authors: | Zhou Qiang |
| |
| Abstract: | In this paper, some corpus-based, statistics-oriented natural language processing tech-niques,include;Shannon's noisy channel model and its applications,n-gram model,the methods to estimate and smooth arguments,preference-based parser and so on,were introduced. It was also discussed that how to use these techniques in the Chinese language processing. |
| |
| Keywords: | Statistics-based processing Corpus Linguistics Natural language processing |
| 本文献已被 CNKI 等数据库收录！ |
|
