首页> 外文会议>Third International Symposium on Information Processing >Chinese News Event 5W1H Elements Extraction Using Semantic Role Labeling
【24h】

Chinese News Event 5W1H Elements Extraction Using Semantic Role Labeling

机译:中文新闻事件使用语义角色标记的5W1H元素提取

获取原文

摘要

To relieve "News Information Overload", classification, summarization and recommendation techniques have been proposed. However, these techniques fail to provide sufficient semantic information about news events. In this paper, considering5W1H (Who, What, Whom, When, Where and How), the full list of elements of a news article, we propose a novel approach to extract event semantic elements. The approach comprises a key event identification step and an event element extraction step. We first use machine learning method to identify the key events of Chinese news stories. Then we employ semantic role labeling (SRL) enhanced by heuristic rules to extract event 5W1Helements. A prototype system is implemented based on proposed approach. Extensive experiments on real online news data sets confirm the reasonability and feasibility of our approach.
机译:为了缓解“新闻信息超载”,已经提出了分类,摘要和推荐技术。但是,这些技术无法提供有关新闻事件的足够语义信息。在本文中,考虑到新闻文章元素的完整列表5W1H(Who,What,Whom,何时,何地和How),我们提出了一种提取事件语义元素的新颖方法。该方法包括关键事件识别步骤和事件元素提取步骤。我们首先使用机器学习方法来识别中文新闻故事的关键事件。然后,我们采用启发式规则增强的语义角色标记(SRL)来提取事件5W1Helements。基于提出的方法实现了原型系统。对真实在线新闻数据集的大量实验证实了我们方法的合理性和可行性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号