A bayesian learning approach to promoting diversity in ranking for biomedical information retrieval

摘要: In this paper, we propose a Bayesian learning approach to promoting diversity for information retrieval in biomedicine and re-ranking model improve performance the biomedical domain. First, computes maximum posterior probability of hidden property corresponding each retrieved passage. Then it iteratively groups passages into subsets according their properties. Finally, these are re-ranked from as our output. There is no need proposed method use any external resource. We evaluate by conducting extensive experiments on TREC 2004-2007 Genomics data sets. The experimental results show effectiveness ranking four years