ABSTRACT – Cloud computing is one of the most useful
environment that provides various information services in which
required information can be retrieved through many web-based
tools and applications. Now the new surge of interest in cloud
computing is accompanied with the exponential growth of data
sizes .There is a need to find the desired content quickly and
efficiently by simply consulting the index. Thus there arises a
question of how to effectively process these immense data sets is
becoming increasingly urgent. Our existing system is searching
the content through ontology in cloud which practically suffers
from maintaining a consistent logic for the input documents
given and taking this advantage into consideration we have
brought in new concepts called Document Retrieval Algorithm.
In this paper we discuss how effectively and efficiently
information can be retrieved from cloud taking into account their
storage space too, where we store the metadata of file in cloud
and not the entire file which holds a lot of space in distributed
environment. Thus we bring in the concept of Named Entity
Recognition and Universal Word List with Term frequency,
which maximizes the information retrieval more effective and
efficient and also to bridge the gap between the semantic web and
the users which reduces the complexity met by them in
information retrieval.