J4 ›› 2013, Vol. 35 ›› Issue (4): 181-185.
• 论文 • 上一篇 下一篇
何中市,刘莉,邢欣来,毛小丽
收稿日期:
修回日期:
出版日期:
发布日期:
基金资助:
重庆科技攻关项目(CSTC 2010AB2001)；中央高校基本科研业务资助项目（CDJXS10181131）
HE Zhongshi,LIU li,XING Xinlai,MAO Xiaoli
Received:
Revised:
Online:
Published:
摘要：
提出了一种中文事件识别方案。该方案在抽取传统特征的同时，根据中文事件的特点，新加入语义角色SR特征构建特征向量，然后采用CRFs进行识别。在SemEval2010评测的TempEval2任务数据上进行实验，该方案识别中文事件的F1(F1measure)值达到85.4%，与未加入语义角色特征相比，提高了3.6%。实验表明本方案在解决中文事件识别问题上有较好的效果。
关键词: 语义角色特征, 特征向量, 条件随机场, 事件识别
Abstract:
This paper proposed a new Chinese events recognition method with a variety of common features plus semantic roles features according to the characteristics of Chinese events and using the feature vector to train a CRFs (Conditional Random Fields, CRFs)classifier. When recognizing the Chinese events, this method achieves the F1 measure of 85.4% which increases by 3.6% compared with no semantic role features on the data supplied by the TempEval2 task of SemEval2010. Experimental results show that the proposed method is benefit to Chinese event recognition.
Key words: semantic role features;feature vector;conditional random fields;Chinese events recognition
何中市,刘莉,邢欣来,毛小丽. 基于语义角色的中文事件识别[J]. J4, 2013, 35(4): 181-185.
HE Zhongshi,LIU li,XING Xinlai,MAO Xiaoli. Chinese events recognition based on semantic role [J]. J4, 2013, 35(4): 181-185.
0 / / 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: http://joces.nudt.edu.cn/CN/
http://joces.nudt.edu.cn/CN/Y2013/V35/I4/181
