全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于条件随机域的中文事件类型识别

, PP. 445-449

Keywords: 事件抽取,事件类型识别,条件随机域

Full-Text   Cite this paper   Add to My Lib

Abstract:

传统的分步骤事件抽取方法中,事件元素识别的结果无法指导事件类型识别,而事件类型识别的效果在很大程度上决定了事件抽取系统的整体性能。文中为解决事件类型识别对元素识别的后向依赖问题,将事件抽取看作序列标注,构建一个改进的条件随机域联合标注模型,将事件类型和事件元素在图模型中同时进行标注。同时,通过触发词嵌入试图解决事件抽取中的数据不平衡问题。ACE2005中文语料上的实验表明,基于该模型的方法提高了事件类型识别的性能,最终F值达到63。53%。

References

[1]  Li Baoli,Chen Yuzhong,Yu Shiwen.Research on Information Extraction: A Survey.Computer Engineering and Application,2003,39(10): 1-5 (in Chinese)(李保利,陈玉忠,俞士汶.信息抽取研究综述.计算机工程与应用,2003,39(10): 1-5)
[2]  Liang Han,Chen Qunxiu,Wu Pingbo.Information Extraction System Based on Event Frame.Journal of Chinese Information Processing,2006,20(2): 40-46 (in Chinese)(梁 晗,陈群秀,吴平博.基于事件框架的信息抽取系统.中文信息学报,2006,20(2): 40-46)
[3]  Ahn D.The Stages of Event Extraction // Proc of the COLING-ACL Workshop on Annotating and Reasoning about Time and Events.Sydney,Australia,2006: 1-8
[4]  Zhao Yanyan,Qin Bing,Che Wanxiang,et al.Research on Chinese Event Extraction.Journal of Chinese Information Processing,2008,22(1): 3-8 (in Chinese)(赵妍妍,秦 兵,车万翔,等.中文事件抽取技术研究.中文信息学报,2008,22(1): 3-8)
[5]  Zheng Chen,Heng Ji.Language Specific Issue and Feature Exploration in Chinese Event Extraction // Proc of the Annual Conference of the North American Chapter of the Association for Computational Linguistics.Colorado,USA,2009: 209-212
[6]  Lafferty J D,McCallum A,Pereira F C N.Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data // Proc of the 18th International Conference on Machine Learning.Williamstown,USA,2001: 282-289

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133