Automatic Extraction Method of Tibetan New Valid Words

Abstract

This paper proposes a model to automatically extract Tibetan new valid words. Through building the dynamic Tibetan corpus from 2009 to 2012, which covers more than 18 Tibetan network media of Tibet, Qinghai, Sichuan, Gansu and Yunnan, we research on the key techniques of Tibetan new valid word extraction: (1) using statistical method to establish Tibetan new word knowledge base, (2) using information entropy to filter Tibetan new valid words, (3) using vector space module similarity calculation to extract Tibetan new valid word.