CAJ | 학술논문

为提高跨语言查询扩展检索精度，在原有跨语言查询扩展基础上，引入降低噪声和孤立点的k-me doid聚类算法，提出避免语义信息丢失或过拟合的择优模型。构建若干个不同维度值的 d维模型，结合奇异值分解和非负矩阵分解法计算文本之间的相似度，选取相似度最大的模型建立双语空间，经过跨语言扩展与权值调整，实现查询扩展优化。实验对比结果表明，该方案有效提高了检索精度，为跨语言查询提供了可参考的模型与算法。
위제고과어언사순확전검색정도，재원유과어언사순확전기출상，인입강저조성화고립점적k-me doid취류산법，제출피면어의신식주실혹과의합적택우모형。구건약간개불동유도치적 d유모형，결합기이치분해화비부구진분해법계산문본지간적상사도，선취상사도최대적모형건립쌍어공간，경과과어언확전여권치조정，실현사순확전우화。실험대비결과표명，해방안유효제고료검색정도，위과어언사순제공료가삼고적모형여산법。
To improve the cross-language query expansion retrieval precision ,based on the original cross-language query expan-sion ,the k-medoid clustering algorithm was introduced to reduce the noise and isolated points ,the merit-based model was pro-posed to avoid the semantic information missing or over-fitting .A number of d-dimensional models were constructed with diffe-rent dimension values combined with the singular value decomposition and the non-negative matrix factorization method to calcu-late the similarity between the texts ,the bilingual model space with the greatest similarity was selected ,through cross-language extensions and weights adjustments ,finally the query expansion optimization was achieved .Experimental comparison results show that the improved scheme can improve the retrieval accuracy effectively ,and it provides a reference model and algorithm queries for the cross-language field .