中文姓名的自动辨识

Identifying Chinese Names in Unrestricted Texts

中文姓名的辨识对汉语自动分词研究具有重要意义。本文提出了一种在中文文本中自动辨识中文姓名的算法。我们从新华通讯社新闻语料库中随机抽取了３００个包含中文姓名的句子作为测试样本。实验结果表明，召回率达到了９９．７７％。

he processing of Chinese names is significant to the approach of Chinese word segmentation. This paper presents an effective algorithm for automatically identifying this sort of proper nouns in Chinese texts. The testing sample, involving 300 sentences each of which contains at least one Chinese names, is extracted at random from the Xinhua News Corpus. The preliminary experiment shows that the recall rate of this algorithm reaches 99.77%.