Context-aware information retrieval and semantic text analysis for very large unstructured data

非常大的非结构化数据的上下文感知信息检索和语义文本分析

• 批准号: 359136-2008
• 负责人: Huang, Xiangji(Jimmy)
• 金额: $ 3.46万
• 依托单位: York University
• 依托单位国家: 加拿大
• 项目类别: Research Tools and Instruments - Category 1 (<$150,000)
• 财政年份: 2007
• 资助国家: 加拿大
• 起止时间: 2007-01-01 至 2008-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=366618
• 关键词: Context; aware; information; retrieval; semantic

With the ever-increasing large amount of digital information available, the need for advanced Information Retrieval (IR) and text analysis systems increases. This wealth of digital information presents a major data-analysis challenge for us. How to manipulate, analyze and understand large quantities of complex data becomes extremely important.Our primary goal of this proposed research is to develop more advanced and novel tools in information technology to search for the most relevant information and discover significant patterns from very large unstructured data. In particular, (1) we will establish an Information Retrieval and Text Analysis Research Lab (IRLab); (2) we will build a context-aware search engine to filter out unnecessary information and implement semantic text analysis tools to effectively extract key elements from free-form unstructured data for improving retrieval performance.The proposed research will lead to more effective information retrieval applications in many domains such as medical health care, Web search, business enterprise search and bioinformatics, which will bring broad benefits to society and people from both academia and industry.

随着数字信息的不断增加，对高级信息检索（IR）和文本分析系统的需求也在增加。这些丰富的数字信息对我们来说是一个重大的数据分析挑战。如何操作、分析和理解大量复杂数据变得非常重要，我们提出的这项研究的主要目标是开发更先进和新颖的信息技术工具，以搜索最相关的信息，并从非常大的非结构化数据中发现重要的模式。具体而言，（1）我们将建立一个信息检索和文本分析研究实验室（IRFab）;（2）我们将建立一个上下文感知的搜索引擎，以过滤掉不必要的信息，并实施语义文本分析工具，以有效地从免费的本文的研究将为医学等领域的信息检索提供更有效的应用医疗保健、网络搜索、商业企业搜索和生物信息学，这将为社会和学术界和工业界的人们带来广泛的利益。