| 引用本文： |
-
李玖一,于洪志,徐涛.藏文文本聚类及其相关技术综述[J].广西科学院学报,2018,34(1):39-45. [点击复制]
- LI Jiuyi,YU Hongzhi,XU Tao.A Summary of Tibetan Text Clustering and Its Related Technologies[J].Journal of Guangxi Academy of Sciences,2018,34(1):39-45. [点击复制]
|
|
| 摘要: |
| 藏文作为一门古老的语言有其独有的规则和特点。随着网络的普及,互联网用户中的藏族同胞迅速增加,网络上的藏文文本也越来越多。利用藏文文本聚类来提供更高效的管理和更良好的用户体验成为近年的研究热点。本文首先介绍了藏文文本聚类的应用背景和相关概念,然后介绍了藏文文本特点和藏文文本聚类的相关技术,讨论了藏文文本建模和聚类算法,最后对藏文聚类发展和应用进行了总结和展望。 |
| 关键词: 藏文文本 聚类算法 文本建模 |
| DOI：10.13657/j.cnki.gxkxyxb.20180227.002 |
| 投稿时间：2017-12-20修订日期：2018-01-09 |
| 基金项目:民族特色农产品多语言网络交易展示平台关键技术集成与应用示范项目(2015BAD29B01)资助。 |
|
| A Summary of Tibetan Text Clustering and Its Related Technologies |
|
LI Jiuyi, YU Hongzhi, XU Tao
|
| (China National Languages Key Laboratory of Information Technology, Northwest University of Nationalities, Lanzhou, Gansu, 730030, China) |
| Abstract: |
| As an ancient language, Tibetan language has its own unique rules and characteristics. With the popularization of the Internet, the number of Tibetan compatriots among Internet users has increased rapidly, and there are more and more Tibetan texts on the Internet. Using Tibetan text clustering to provide more efficient management and user experience has become a hot topic in recent years. This article first introduces the application background and related concepts of Tibetan text clustering. Then it introduces the characteristics of Tibetan texts and the related technologies of Tibetan text clustering. After that, the Tibetan text modeling and clustering algorithms of Tibetan text are discussed. Finally, the development and application of Tibetan language clustering are summarized and prospected. |
| Key words: Tibetan text clustering algorithms text modeling |
