| 基于条件随机场的英文产品命名实体识别 |
| |
| 引用本文： | 张朝胜,郭剑毅,线岩团,余正涛,雷春雅,王海雄. 基于条件随机场的英文产品命名实体识别[J]. 计算机工程与科学, 2010, 32(6): 115-117. DOI: 10.3969/j.issn.1007130X.2010. |
| |
| 作者姓名： | 张朝胜 郭剑毅 线岩团 余正涛 雷春雅 王海雄 |
| |
| 作者单位： | 1. 昆明理工大学信息工程与自动化学院,云南,昆明,650051
2. 昆明理工大学信息工程与自动化学院,云南,昆明,650051;云南省计算机技术应用重点实验室智能信息处理研究所,云南,昆明,650051 |
| |
| 基金项目： | 国家自然科学基金，云南省自然科学基金重点项目，云南省中青年学术技术带头人后备人才培养基金，云南省教育厅基金重点项目 |
| |
| 摘 要： | 英文产品命名实体识别目前国内外研究得较少,本文针对TREC 2009英文产品命名实体(EPNE)识别的任务,首次提出了一种基于条件随机场模型(CRF)的英文产品命名实体识别方法。在条件随机场中,该方法以词作为切分粒度,充分利用上下文和英文产品名特有的指示信息作为分类特征,结合手工构建的品牌词表进行建模。实验表明,该方法获得了较好的结果,英文产品实体识别准确率达到93.6%,召回率达到92.4%。
|
| 关 键 词： | 英文产品 条件随机场 特征选择 命名实体识别 |
| 收稿时间： | 2009-09-26 |
| 修稿时间： | 2009-12-21 |
Named Entity Recognition of the Products with English Based on Conditional Random Fields |
| |
| ZHANG Chao-sheng,GUO Jian-yi,XIAN Yan-tuan,YU Zheng-tao,LEI Chun-ya,WANG Hai-xiong. Named Entity Recognition of the Products with English Based on Conditional Random Fields[J]. Computer Engineering & Science, 2010, 32(6): 115-117. DOI: 10.3969/j.issn.1007130X.2010. |
| |
| Authors: | ZHANG Chao-sheng GUO Jian-yi XIAN Yan-tuan YU Zheng-tao LEI Chun-ya WANG Hai-xiong |
| |
| Affiliation: | (1.School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650051;2.Institute of Intelligent Information Processing,Yunnan Provincial Computer Technology Application Key Laboratory,Kunming 650051,China) |
| |
| Abstract: | Recently, as the scarce research of Named Entity Recognition of the Products with English domesticaly and abroad, this paper aims at the task of TREC 2009, and proposes a method for the Named Entity Recognition of the Products with English based on the Conditional Random Fields model. In the conditional random field, this paper adopts word as the grain processing unit; uses the context information and especial cue information of English product names as the features of recognition, and adopts the artificially constructed dictionary to build the model. A good result has been obtained by the experiment and the accuracy rate of the English product entity recognition is up to 93.6%, and the recall rate 92.4%. |
| |
| Keywords: | english product CRF feature selection recognition of named entity |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与科学》浏览原始摘要信息 |
|
点击此处可从《计算机工程与科学》下载免费的PDF全文 |
|
