PSG: a two-layer graph model for document summarization
PSG: a two-layer graph model for document summarization
复制标题
DOI：
10.1007/s11704-013-2292-2
复制
发表时间：
2014-02
影响因子：
4.2
通讯作者：
Heng Chen;Hai Jin;Feng Zhao
中科院分区：
文献类型：
--
作者：
Heng Chen;Hai Jin;Feng Zhao
图模型以句子作为图节点，句子之间的相似度作为边，在文档摘要中得到了广泛的应用。本文提出了一种新颖的文档摘要图模型，该模型不仅利用句子相关性，还利用句子中包含的短语相关性信息。总之，我们构建了一个短语-句子两层图结构模型（PSG）来总结文档。我们使用此模型进行通用文档摘要和以查询为中心的摘要。实验结果表明我们的模型大大优于现有的工作。
Graph model has been widely applied in document summarization by using sentence as the graph node, and the similarity between sentences as the edge. In this paper, a novel graph model for document summarization is presented, that not only sentences relevance but also phrases relevance information included in sentences are utilized. In a word, we construct a phrase-sentence two-layer graph structure model (PSG) to summarize document(s). We use this model for generic document summarization and query-focused summarization. The experimental results show that our model greatly outperforms existing work.