| 中文事件时序关系的标注和分类方法 |
| |
| 引用本文： | 郑,新,李培峰,朱巧明.中文事件时序关系的标注和分类方法[J].计算机科学,2015,42(7):276-279, 313. |
| |
| 作者姓名： | 郑 新 李培峰 朱巧明 |
| |
| 作者单位： | 苏州大学计算机科学与技术学院 苏州215006江苏省计算机信息处理技术重点实验室 苏州215006 |
| |
| 基金项目： | 本文受国家自然科学基金(61331011,61272260),国家863项目(2012AA011102)资助 |
| |
| 摘 要： | 事件时序关系的研究在问答系统、信息抽取和文本自动摘要等自然语言处理领域起着重要的作用。首先借鉴英文的标注方法,将中文事件的时序关系分为4类,并给出了具体的标注方法。然后给出了一个中文时序关系的分类方法。最后,在标注语料库上测试了中文事件时序关系分类的性能,结果表明该方法优于规则方法。
|
| 关 键 词： | 事件 时序关系 语料库 |
Annotation and Classification of Temporal Relation between Chinese Events |
| |
| ZHENG Xin LI Pei-feng ZHU Qiao-ming.Annotation and Classification of Temporal Relation between Chinese Events[J].Computer Science,2015,42(7):276-279, 313. |
| |
| Authors: | ZHENG Xin LI Pei-feng ZHU Qiao-ming |
| |
| Affiliation: | School of Computer Science and Technology,Soochow University,Suzhou 215006,China Provincial Key Laboratory for Computer Information Processing Technology of Jiangsu,Suzhou 215006,China |
| |
| Abstract: | The research on temporal relation between events plays an important role in natural language processing,such as question answering system,information extraction and text summarization.We first focused on the temporal relation between Chinese events,divided it into four categories and presented an annotation method.Then we proposed a method to classify the temporal relation between Chinese events.Finally,the results of the classification on the annotated corpus show that our method outperforms the rule-base baseline. |
| |
| Keywords: | Event Temporal relation Corpus |
|
|
点击此处可从《计算机科学》下载全文 |
|
