计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (20): 100-104.DOI: 10.3778/j.issn.1002-8331.1604-0231

• 模式识别与人工智能 • 上一篇    下一篇

机械设计领域的命名实体识别研究

陈秋瑗1,2,程  光1,2,李  迪1,2,张  建1,2   

  1. 1.北京联合大学 机器人学院,北京 100020
    2.北京市智能机械创新设计服务工程技术研究中心,北京 100020
  • 出版日期:2017-10-15 发布日期:2017-10-31

Named entity recognition for mechanical design and manufacturing area

CHEN Qiuyuan1,2, CHENG Guang1,2, LI Di1,2, ZHANG Jian1,2   

  1. 1.College of Robotics, Beijing Union University, Beijing 100020, China
    2.Beijing Engineering Research Center of Smart Mechanical Innovation Design Service, Beijing 100020, China
  • Online:2017-10-15 Published:2017-10-31

摘要: 命名实体识别技术在自然语言处理技术中占有重要的地位,通用的方法不能很好地解决机械领域的识别问题。基于字符串之间紧密相邻程度等统计特征,定义不同词之间紧密相连的程度,从而识别机械领域的领域词。通过计算特征值,用逻辑回归的方法确定相邻字串的紧密相邻程度,从而发现新词。该方法对比通用的方法准确率和召回率得到了提高,更好地识别机械领域的领域词。

关键词: 命名实体识别, 机械领域, 逻辑回归, 紧密相邻

Abstract: Named entity recognition has wide applications in the area of natural language processing, but the common methods cannot accurately identify the proper nouns in manufacture area. In order to solve the named entity recognition for mechanical design and manufacturing area, this paper proposes a new machine learning based method. It carefully finds some statistical features, and then uses the logistic regression algorithm to calculate the tightness between two adjacent strings. The proposed method can recognize proper nouns more accurately and efficiently for mechanical design and manufacturing area.

Key words: named entity recognition, mechanical design, logistic regression, tightness