Using Hedges to Enhance a Disease Outbreak Report Text Mining System
Using Hedges to Enhance a Disease Outbreak Report Text Mining System
复制标题
DOI：
10.3115/1572364.1572384
复制
发表时间：
2009-06
期刊：
影响因子：
--
通讯作者：
Mike Conway;S. Doan;Nigel Collier
中科院分区：
文献类型：
--
作者：
Mike Conway;S. Doan;Nigel Collier
对于国家政府和世界卫生组织等国际组织来说，在早期阶段识别严重传染病疫情都是一项重要任务。在这些情况下，文本挖掘和信息提取系统可以通过从在线文本新闻中自动识别疫情爆发的最初迹象，提供重要、低成本和及时的预警系统。疾病暴发报告的一个有趣的特点---据我们所知，以前没有研究过---是他们使用推测性语言（对冲）来描述不确定的情况。本文介绍了两种使用对冲，以加强BioCaster疾病爆发报告文本挖掘系统。
Identifying serious infectious disease outbreaks in their early stages is an important task, both for national governments and international organizations like the World Health Organization. Text mining and information extraction systems can provide an important, low cost and timely early warning system in these circumstances by identifying the first signs of an outbreak automatically from online textual news. One interesting characteristic of disease outbreak reports --- which to the best of our knowledge has not been studied before --- is their use of speculative language (hedging) to describe uncertain situations. This paper describes two uses of hedging to enhance the BioCaster disease outbreak report text mining system.