Auto complete using graph mining: A different approach

Autocomplete feature is widely used in search interfaces to assist users in their search. Autocomplete helps users by giving list of options based on characters entered in the search field. Significant amount of work has been done in this field, but the techniques used are not efficient or relevant when it comes to search within specific content like a text file, a document or a web page. This calls for different approaches such as ours. Our proposed method is based on preprocessing, graph mining, and hashing for generating the suggestion list. The suggestion list provided by our proposed method is more relevant because the list is document specific. Test results from our proposed method show that our proposed method significantly outperforms existing document specific autocomple search techniques.