| 一种基于语料库的词义消歧策略 |
| |
| 引用本文： | 郭池,陈家骏,王启祥.一种基于语料库的词义消歧策略[J].计算机工程与应用,2003,39(35):33-36,65. |
| |
| 作者姓名： | 郭池 陈家骏 王启祥 |
| |
| 作者单位： | 南京大学计算机科学与技术系,南京,210093;南京大学计算机软件新技术国家重点实验室,南京,210093 |
| |
| 基金项目： | 国家863高技术研究发展计划项目经费资助(编号:2001AA114102) |
| |
| 摘 要： | 词义消歧一直是一个难点,同时,也是很多领域都需解决的一个环节。该文首先介绍了目前基于语料库进行词义消歧方法的研究进展和各自的特点,在此基础上探讨了一种基于实例和基于统计的方法(即基于语料库的两种主流方法)相结合的混合策略,并对其可能性和优越性进行了讨论。
|
| 关 键 词： | 词义消歧 机器翻译 语料库 基于实例 基于统计 混合策略 |
| 文章编号： | 1002-8331-(2003)35-0033-04 |
An Approach to Corpus-based Word Sense Disambiguation |
| |
| Guo Chi,Chen Jiajun Wang Qixiang.An Approach to Corpus-based Word Sense Disambiguation[J].Computer Engineering and Applications,2003,39(35):33-36,65. |
| |
| Authors: | Guo Chi Chen Jiajun Wang Qixiang |
| |
| Abstract: | Word Sense Disambiguation(WSD)is a difficult issue in many fields,e.g.,machine translation,information retrieval and hypertext navigation,context and thematic analysis etc.This paper firstly introduces the recent research progress and characteristic of each corpus-based WSD approach,and then discusses the feasibility and advantage of a policy combining an example-based method and a statistical method,which are two primary corpus-based methods. |
| |
| Keywords: | Word Sense Disambiguation(WSD) Machine Translation(MT ) Corpus Example -based Statistical Combined method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
