藏文信息处理研究进展

藏文有着悠久的历史,是藏族人民交流思想的工具。1997年,藏文编码字符集国际、国家标准的制定作为藏文信息处理的开始,至今正好20年。这20年中藏文信息处理起步、发展,取得了较好的成绩。本文简要回顾了藏文信息处理中字、词、句、段、篇的特点、处理方法及取得的典型成果,也回顾了藏语资源建设和应用研究取得的成果,并对藏文信息处理未来的发展方向进行展望。希望能为迈入藏文信息处理的初学者展示一个藏文信息处理发展的脉络,提供一个参考。

Research on Tibetan Information Processing

Tibetan has a long history and is a tool for Tibetan people to exchange ideas. In 1997, the establishment of the unicode and national standards of Tibetan-coded character sets was the beginning of Tibetan information processing, and it has been exactly 20 years. In the past 20 years, Tibetan information processing has started and developed, and good results have been achieved. This article briefly reviewed the characteristics, processing methods and typical achievements of syllable, words, sentences, paragraphs and articles in Tibetan information processing. It also reviewed the achievements of Tibetan language resources construction and application research. The future development of Tibetan information processing was also been prospected. I hope it can demonstrate the context of the development of Tibetan information processing and provide a reference for beginners entering Tibetan information processing.