|
|||||
|
|
| 汉语框架网中未登录词元的框架选择 | |
| 引用本文： | 陈学丽,李 茹,王 赛,王智强. 汉语框架网中未登录词元的框架选择[J]. 中文信息学报, 2014, 28(3): 48-54 |
| 作者姓名： | 陈学丽 李 茹 王 赛 王智强 |
| 作者单位： | 1. 山西大学 计算机与信息技术学院,山西 太原 030006; 2. 山西大学 计算智能与中文信息处理教育部重点实验室,山西 太原 030006 |
| 基金项目： | 国家自然科学基金(60970053,61373082);国家语委“十二五”科研规划项目(YB125-19);国家863高技术研究发展计划项目(2006AA0lZ142);山西省回国留学人员科研资助项目(20B-05) |
| 摘 要： | 汉语框架网的低覆盖率导致汉语句子中存在许多未登录的词元,严重制约着汉语的框架语义分析任务。针对未登录词元的框架识别问题,该文借助同义词词林的词义信息,提出基于平均语义相似度计算及最大熵模型两种方法,采用静态特征与动态特征相结合的特征选择方法。实验证明,这两种方法都能有效地实现未登录词元的框架选择,基于相似度计算的方法(TOP-4)获得78.61%的准确率;基于最大熵的方法结果可达87.29%,同时在新闻语料上达到了75%的准确率。 |
| 关 键 词： | 汉语框架网 未登录词元 词义信息 |
Frame Selection for Unknown Lexical Units from Chinese FrameNet |
|
| CHEN Xueli,LI Ru,WANG Sai,WANG Zhiqiang. Frame Selection for Unknown Lexical Units from Chinese FrameNet[J]. Journal of Chinese Information Processing, 2014, 28(3): 48-54 | |
| Authors: | CHEN Xueli LI Ru WANG Sai WANG Zhiqiang |
| Affiliation: | 1. School of Computer & Information Technology, Shanxi University, Taiyuan, Shanxi 030006, China; 2. Key Laboratory of Ministry of Education for Computation Intelligence & Chinese Information Processing, Taiyuan, Shanxi 030006, China |
| Abstract: | The low coverage of Chinese FrameNet leads to many unknown lexical units and restricts the frames semantic analysis for Chinese. In order to identify frames for unknown lexical units, this paper proposes two methods based on Tongyici CiLin: the Average Semantic Similarity method and Maximum Entropy (ME-based) method which both combine the static features and dynamic features. Experiments show that the two methods can effectively identify the frame of unknown lexical units: the accuracy of the similarity-based method is 78.61% considering Top-4 candidates; the Top-1 accuracy of the ME-based method for the same test set is 87.29% (and 75% for another news texts). |
| Keywords: | Chinese FrameNet unknown lexical unit word sense information |
| 本文献已被 CNKI 等数据库收录！ | |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |