In today’s traditional search approach, when a user types a keyword for searching, the search engine searches through its collection of document for the typed keyword. It checks for the exact typed keyword in all the documents and returns only those documents which contained it and ranks it on some ranking algorithm.
Words which are same in meaning but spelled out differently would be totally
ignored in the Search results (SERPs.) Plus the results retrieved would have 50%
sites which are totally irrelevant to the search query.
To address this important issue of presenting only relevant search results,
Latent Semantic Indexing or LSI was proposed be many researchers as a new improved method of retrieval system.
In Latent Semantic Indexing, not only keywords contained in a document would be
recognized, it would see the document collection as a whole, to establish which
other documents contain some of those same words. In LSI, documents that have
words in common is considered semantically close, and ones with few words in
common to be semantically distant.
To help our visitors to understand LSI even better, we have written collection of articles. These articles are very informative and would provide a necessary insight into this NEW Search algorithm from Google.
Articles
|