Chinese Web Information Retrieval Based on Shallow Parsing

To improve the retrieval performance, shallow parsing technique for text was introduced for Chinese Web information retrieval. Firstly, predicate, prepositive nominal component and succedent nominal component close to the predicate were extracted from Chinese sentence. Then, semantic vector of Chinese text was acquired based on converting predicate and nominal component to conception. An algorithm was presented for similarity calculating of semantic vector, and a Chinese Web information retrieval model was designed. The model evaluates the matching degree between indexed documents and users' interests based on semantic similarity calculating. Users' interests were expressed by delivering representative documents. Experimental results show that the precision is improved observably compared with the popular Web search engine.