| 基于领域文献的未登录词识别方法研究 |
| |
| 引用本文： | 徐坤,曹锦丹.基于领域文献的未登录词识别方法研究[J].情报杂志,2012(1):172-174,171. |
| |
| 作者姓名： | 徐坤 曹锦丹 |
| |
| 作者单位： | 吉林大学公共卫生学院 |
| |
| 摘 要： | 提出了一种针对领域文献的易于实现且具有较高准确率的未登录词自动识别方法。通过该方法生成未登录词表,可提高中文自动分词效果,弥补领域主题词表更新慢的不足,方便对领域文献的后续处理,进而提高科研工作者利用文献的效率。
|
| 关 键 词： | 未登录词 自然语言处理 领域文献 |
The Study on Out-of-Vocabulary Automatic Identification Method Based on Domain Literature |
| |
| XU Kun,CAO Jindan.The Study on Out-of-Vocabulary Automatic Identification Method Based on Domain Literature[J].Journal of Information,2012(1):172-174,171. |
| |
| Authors: | XU Kun CAO Jindan |
| |
| Institution: | (School of Public Health,Jilin University,Changchun 130021) |
| |
| Abstract: | This paper presents an out-of-vocabulary automatic identification method based on domain literature.The method proposed has a high accuracy,and is easy to implement.The out-of-vocabulary list generated by this method can improve the Chinese word segmentation accuracy and make up for the lack of the slow thesaurus update,so it can facilitate the subsequent processing on domain literature and improve the utilization efficiency of domain literature. |
| |
| Keywords: | out-of-vocabulary natural language processing domain literature |
| 本文献已被 CNKI 等数据库收录！ |
|
