N-gram and local context analysis for Persian text retrieval

The Persian language is one of the languages in Midde-East, so there are significant amount of Persian documents available on the Web. But there are relatively few studies on retrieval of Persian documents in the literature. In this experimental study, we assessed term and N-gram based vector space model and a query expansion method namely, Local Context Analysis using different weighting schemes on a realistic corpus containing 160000+ news articles. Then we compared our results with previous works reported on Persian language. Our experimental results show that among the assessed methods, 4-gram based vector space model with Lnu.ltu weighting scheme has acceptable performance and Local Context Analysis has the best performance for Persian text retrieval so far.