Concept Representation (Embedding) and Semantic Relatedness

Document clustering is an efficient way to get insight into large text collections. Due to the personalized nature of document clustering, even the best fully automatic algorithms cannot create clu…

In this project, we use skip-gram model to embed Wikipedia Concepts and Entities. The English version of Wikipedia contains more than five million pages, which suggest its capability to cover many …

Sunflower is a tool for extracting and representing category graph of words. The key idea is using different versions (languages) of Wikipedia to generate the category graph of the input.