• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Bioinformatics and Computational Biology >EVENT EXTRACTION WITH COMPLEX EVENT CLASSIFICATION USING RICH FEATURES
【24h】

EVENT EXTRACTION WITH COMPLEX EVENT CLASSIFICATION USING RICH FEATURES

机译：利用丰富的功能进行复杂事件分类的事件提取

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Biomedical Natural Language Processing (BioNLP) attempts to capture biomedical phenomenanfrom texts by extracting relations between biomedical entities (i.e. proteins andngenes). Traditionally, only binary relations have been extracted from large numbersnof published papers. Recently, more complex relations (biomolecular events) have alsonbeen extracted. Such events may include several entities or other relations. To evaluatenthe performance of the text mining systems, several shared task challenges have beennarranged for the BioNLP community. With a common and consistent task setting, thenBioNLP’09 shared task evaluated complex biomolecular events such as binding and regulation.nFinding these events automatically is important in order to improve biomedicalnevent extraction systems. In the present paper, we propose an automatic event extractionnsystem, which contains a model for complex events, by solving a classification problemnwith rich features. The main contributions of the present paper are: (1) the proposalnof an effective bio-event detection method using machine learning, (2) provision of anhigh-performance event extraction system, and (3) the execution of a quantitative errornanalysis. The proposed complex (binding and regulation) event detector outperformsnthe best system from the BioNLP’09 shared task challenge
机译：生物医学自然语言处理（BioNLP）试图通过提取生物医学实体（即蛋白质和基因）之间的关系来捕获文本中的生物医学现象。传统上，仅从大量已发表的论文中提取二进制关系。近来，还提取了更复杂的关系（生物分子事件）。此类事件可能包括几个实体或其他关系。为了评估文本挖掘系统的性能，已经为BioNLP社区安排了一些共同的任务挑战。通过共同且一致的任务设置，然后BioNLP’09共享任务评估了复杂的生物分子事件，例如结合和调控。n自动发现这些事件对于改善生物医学事件提取系统非常重要。通过解决具有丰富特征的分类问题，本文提出了一种自动事件提取系统，该系统包含复杂事件的模型。本文的主要贡献是：（1）提出了一种使用机器学习的有效生物事件检测方法的建议；（2）提供了高性能事件提取系统；（3）执行了定量误差分析。拟议的复杂（绑定和规则）事件检测器的性能优于BioNLP’09共享任务挑战中的最佳系统

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