点击次数：

论文类型： 期刊论文

发表时间： 2013-08-15

发表刊物： Journal of Computational Information Systems

收录刊物： EI、Scopus

卷号： 9

期号： 16

页面范围： 6343-6350

ISSN号： 15539105

摘要： This paper proposes a bilingual biomedical topic space model in which both Chinese and English abstract are represented by improved Latent Dirichlet Allocation with SVD and NMF decomposition smoothing methods. The improved LDA-based method is used to calculate the relationship between query and document and combine the results of different matrix factorization. A set of different dimension models is set up, with the help of which we can achieve bilingual cross-language indexing. The experimental results show that our method can improve the retrieval accuracies effectively. ? 2013 Binary Information Press.