@article{(Open Science Index):https://publications.waset.org/pdf/10884,
	  title     = {Advanced Information Extraction with n-gram based LSI},
	  author    = {Ahmet Güven and  Ö. Özgür Bozkurt and  Oya Kalıpsız},
	  country	= {},
	  institution	= {},
	  abstract     = {Number of documents being created increases at an
increasing pace while most of them being in already known topics
and little of them introducing new concepts. This fact has started a
new era in information retrieval discipline where the requirements
have their own specialties. That is digging into topics and concepts
and finding out subtopics or relations between topics. Up to now IR
researches were interested in retrieving documents about a general
topic or clustering documents under generic subjects. However these
conventional approaches can-t go deep into content of documents
which makes it difficult for people to reach to right documents they
were searching. So we need new ways of mining document sets
where the critic point is to know much about the contents of the
documents. As a solution we are proposing to enhance LSI, one of
the proven IR techniques by supporting its vector space with n-gram
forms of words. Positive results we have obtained are shown in two
different application area of IR domain; querying a document
database, clustering documents in the document database.},
	    journal   = {International Journal of Computer and Information Engineering},
	  volume    = {2},
	  number    = {5},
	  year      = {2008},
	  pages     = {1551 - 1556},
	  ee        = {https://publications.waset.org/pdf/10884},
	  url   	= {https://publications.waset.org/vol/17},
	  bibsource = {https://publications.waset.org/},
	  issn  	= {eISSN: 1307-6892},
	  publisher = {World Academy of Science, Engineering and Technology},
	  index 	= {Open Science Index 17, 2008},
	}