Modified information retrieval model based on markov network

Abstract

Information retrieval model is still can not achieve satisfactory performance. Many researches have shown that better term weighting method and model useful information in information retrieval can improve retrieval performance. In this paper we propose a modified information retrieval model based on Markov network, which model the related information using Markov network and use query information to modify term weighting, which can make the relevant document rank high. Experiment shows our model has better performance than baseline model. © Springer-Verlag Berlin Heidelberg 2012.