Research and Implementation of Tibetan Word Segmentation Based on Syllable Methods

摘要：

　　Tibetan word segmentation(TWS)is an important problem in Tibetan information processing,while abbreviated word recognition is one of the key and most difficult problems in TWS.Most of the existing methods of Tibetan abbreviated word recognition are rule-based approaches,which need vocabulary support.In this paper,we propose a method based on sequence tagging model for abbreviated word recognition,and then implement in TWS systems with sequence labeling models.The experimental results show that our abbreviated word recognition method is fast and effective and can be combined easily with the segmentation model.This significantly increases the effect of the Tibetan word segmentation.

作者: Jing Jiang Yachao Li Tao Jiang Hongzhi Yu

作者单位: Key Laboratory of National Language Intelligent Processing(Northwest University for Nationalities),Lanzhou,Gansu,730030,China

会议类型: 国际会议

会议名称: The 1st International Symposium on Application of Materials Science and Energy Materials (SAMSE 2017)

会议地点: 上海

会议语种:英文

页码: 1-6

在线出版日期: 2017-12-28（万方平台首次上网日期，不代表论文的发表时间）