摘要
This paper propose a method for sentence ordering in multi-doucument summarization task, which combine support vector machine (SVM) and Grey Model(GM). Firstly, the method train the SVM with sentences of source documents and predict sentences sequence of summary as primary dataset. Secondly, using Grey Model to process the primary dataset, and achieve the final sequence of summary sentences. Experiments on 100 summ1aries showed this method provide a much higher precision than probabilistic model in sentence ordering task.
- 出版日期2010