摘要
分析了商品文本中药物名称和化学物质名称分词后特征,试图以规则模型和统计模型相结合的方法进行商品文本中药物名称和化学物质名称的辨识.实验结果表明:机器识别可以获得一定的准确率.
The feature of vocabularies about medicines and chemicals in the separated Chinese commodity text is analyzed. An approach combined rule model and probability method is designed to identify the two types of vocabularies in Chinese commodity text. A smallscale test is done. A lot of these vocabularies can be identified correctly.
出处
《烟台大学学报(自然科学与工程版)》
CAS
2002年第4期280-285,共6页
Journal of Yantai University(Natural Science and Engineering Edition)