一种基于神经网络模型的句子排序方法

句子排序是多文本摘要中的重要问题,合理地对句子进行排序对于摘要的可读性和连贯性具有重要意义。该文首先利用神经网络模型融合了五种前人已经提出过的标准来决定任意两个句子之间的连接强度,这五种标准分别是时间、概率、主题相似性、预设以及继承。其次,该文提出了一种基于马尔科夫随机游走模型的句子排序方法,该方法利用所有句子之间的连接强度共同决定句子的最终排序。最终,该文同时使用人工和半自动方法对句子排序的质量进行评价,实验结果表明该文所提出方法的句子排序质量与基准算法相比具有明显提高。

A Neural Network Model Based Sentence Ordering Method for Multi-document Summarization

Sentence ordering is an important task in multi-document summarization. For this purpose, we first use neural network model to incorporate five proposed criteria for sentence connection, namely chronology, probabilistic, topical-closeness, precedence, and succession. Then, a sentence ordering method based on Markov random walk model is proposed, which determines the final ordering of the sentences based on the strength of connection between them. Examined by the semi-automatic and a subjective measures, the proposed method achieves obviously better sentence order compared with the baseline algorithms in the experiments.