|Title: " Semantic Search Engine "|
Abstract— The ability to accurately retrieve the required results from a huge database present over the internet is important. Web search engine based on semantics gives precise results. An empirical method is proposed to provide a semantic wise search that uses in one hand, a technical English dictionary and on the other hand, a page count based metric and a text snippet based metric retrieved from an existing web search engine. To identify the numerous semantic relations between the words, a novel pattern extraction algorithm and a pattern clustering algorithm is proposed. The page counts based co-occurrence measures and lexical pattern clusters extracted from snippets is learned using support vector machines. Integrate the page count, text snippet and dictionary based metric to accurately measure the semantic similarity search compared to normal search. .
Keywords — Web search engine, Pattern extraction, Pattern clustering , natural language processing, co-occurrence measures, snippet, Technical dictionary.