Context Exploration: An Effective Way to Enhance Duplication Detection

作为一个重要的数据质量问题，有效的重复检测在数据管理中具有重要的现实意义，特别是在商业、健康和国家安全等大规模信息系统中。该项目旨在通过提供一个通用的、独立于域的框架来显著提高重复检测，从而为几乎每个信息系统提供独特的价值。这些前沿技术的发展有可能成为数据重复检测研究的新方向。该项目将使我们有机会促进澳大利亚开发尖端技术的能力，并有可能增加澳大利亚在这一领域的形象。

As a vital data quality problem, effective duplication detection has practical significance in data management, in particular in large scale information systems such as in business, health and national security. This project aims to be a unique value to virtually every information systems by providing a general, domain-independent framework which is comprehensive to significantly improve the duplication detection. The developed cutting-edge technologies are potential to be a new direction of data duplication detection study. This project will allow us to avail an opportunity to promote Australia's capability in developing sophisticated technologies and are potential to add to Australia's profile in this area.