基于综合权重的多文档关键词抽取算法

Multi-document Keywords Extraction Algorithm Based on Integrated Weights

多文档关键词抽取是进行在多篇文献中找出最能反映整体主题的关键词。对几种关键词抽取算法进行了介绍,分析了各自的优缺点,在TF/PDF算法的基础上,采用文献内和文献间综合权重的方法。

Multi-document keywords extraction is carried out in many articles in the literature to identify best to reflect the overall theme of the keywords.Extraction algorithm for several keywords were introduced to analyze their respective advantages and disadvantages,in the TF/PDF algorithm,based on the use of literature and literature within a comprehensive inter-weighting method,presents a weight based on an integrated multi-document keywords extraction algorithm ITF/PDF.The ITF/PDF extraction results with TF/PDF extraction results were compared with experimental results show that,ITF/PDF can be more accurate in a multi-document extract the appropriate keywords.