关键词: 命名实体识别, 转移学习, 准确率, 召回率

Abstract: Chinese named entity recognition is widely used in many important areas. To improve the precision and recall of recognition, a new algorithm for Chinese named entity recognition based on transformation learning is proposed in this paper. The central idea behind Transformation-Based Learning（TBL） is to start with some simple solution to the problem, and apply transformations at each step. The transformation which results in the largest benefit is selected and applied to the problem. The algorithm stops when the selected transformation does not modify the data in enough space. This paper puts forward a method to obtain the rule template and constraints file. According to this, a completed Chinese named entity recognition model is proposed. Using this model to experiment, the precision and recall of named entity recognition get a better result.

Key words: named entity recognition, transformation-based learning, precision, recall