语义相似度或关联度计算是目前计算机科学和人工智能的一个重要研究课题，主要原因是语义相似度或关联度是许多信息处理的共性问题。随着新的网络知识库（即半结构化或结构化语义大数据，如Wikipedia和Linked Data）的发展，如何集成这些新型海量语义信息来研究概念语义相似度或关联度计算是一个很有意义的问题。本项目在申请人及其团队已有工作的基础上研究概念语义相似度或关联度计算方法及其评价。理论上主要研究多知识源下概念语义相似度或关联度计算的理论框架。技术上主要研究多知识源下面向海量语义信息的概念语义相似度或关联度高效计算方法，并建立概念语义相似度或关联度计算方法的评价基准。应用上以概念语义相似度或关联度作为技术工具研究基于语义的教育大数据服务（基于语义相似度或关联度的海量教育数字资源检索或分类）。这些研究将对计算机科学和人工智能的理论及技术发展产生一定的积极影响。

Semantic similarity or relatedness computation is an important research field of computer science and artificial intelligence, mainly because the semantic similarity or relatedness is a common problem in much information processing. With the development of new Web knowledge bases (i.e., semi-structured or structured semantic Big Data such as Wikipedia and Linked Data), how to investigate the concept semantic similarity or relatedness computation by integrating these novel massive semantic information is a very meaningful research problem. The project will study concept semantic similarity or relatedness computation approaches and their evaluation using multiple knowledge sources based on the existing works of this project group..In theory this project will study the theoretical framework of concept semantic similarity or relatedness computation using multiple knowledge sources. In technology this project will investigate some efficient computation approaches of concept semantic similarity or relatedness for massive semantic information and construct the evaluation benchmarks for the computation approaches of concept semantic similarity or relatedness. In applications this project will study semantics based Big Data services in education (i.e., semantic similarity or relatedness based information retrieval or classification of massive education digital resources) by making use of concept semantic similarity or relatedness to act as a technological tool..The research results of this project will have a certain impact on the theoretical and technical development of computer science and artificial intelligence.