Domain-Specific Semantic Retrieval of Institutional Repository Based on Query Extension

Researchers have found that most institutional repositories are still using the retrieval technology based on keywords, but because the information resource of which they contain are abundant and highly specialized, such retrieval techniques often can not satisfy the users. This paper designs and implements a Domain-Specific Semantic Retrieval of Institutional Repository, using semantic dictionary WordNet to perform word sense disambiguation and Extension, and the results obtained by filtering the domain dictionary, and take advantage of the open source Lucene search engine tools to complete the document retrieval. Experimental results show that there is improvement in terms of coverage and precision.