"Large Scale Named Entity Recognition for the Web"

Supervised by Professor F Ciravegna

Abstract

This paper gives a detailed description of the current process of the project of large scale named entity recognition. People search for information on the web but usually it is difficult to exactly locate the information they need because entities with the same name appear. Those names serves as an identifier of the entities, however normally they are not able to define the entities uniquely. The aim of the project is to set up an algorithm suitable to classify the named entities in large scale and build Uniform Resource Identifier (URI) for the entities instead of their names. Presently the work is focusing on documentation classification. Some Literal material of URI is also read so far.