Augmented vector space model for passage intention classification in Chinese agricultural prescription documents

作者：Liang Yongquan; Liu Tong; Ni Weijian^*

来源：Journal of Computational Information Systems, 2014, 10(1): 101-108.

DOI：10.12733/jcis8628

• Agricultural prescription
• Classification performance
• Data set
• Experimental comparison
• Feature combination
• NAtural language processing
• Text mining
• Vector space models

Passage-level natural language processing has received increasing attentions in recent years. This paper addresses the problem of passage intention classification for agricultural prescription documents. The proposed approach is based on supervised learning. In order to give a simple yet effective representation for passages in agricultural prescription documents, we augment the traditional Vector Space Model (VSM) widely used in text mining by 2-gram features. Besides, a set of third-party features with priori high class-discriminability are extracted using a third-party resource. We give comprehensive experimental comparisons of various learning algorithms and feature combinations using real world data set. The experimental results indicate that our approach offers promising classification performance.

• 出版日期2014
• 单位山东科技大学